lemonhat commited on
Commit
66546a2
·
verified ·
1 Parent(s): 913ddac

Add files using upload-large-folder tool

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: other
4
+ base_model: meta-llama/Llama-3.2-3B-Instruct
5
+ tags:
6
+ - llama-factory
7
+ - full
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: agenttuning_v4_15k_tag4
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # agenttuning_v4_15k_tag4
18
+
19
+ This model is a fine-tuned version of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) on the agenttuning_v4_15k_tag4 dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.4036
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 5e-06
41
+ - train_batch_size: 1
42
+ - eval_batch_size: 1
43
+ - seed: 42
44
+ - distributed_type: multi-GPU
45
+ - num_devices: 4
46
+ - total_train_batch_size: 4
47
+ - total_eval_batch_size: 4
48
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
49
+ - lr_scheduler_type: cosine
50
+ - num_epochs: 1
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss |
55
+ |:-------------:|:------:|:----:|:---------------:|
56
+ | 0.5004 | 0.4237 | 100 | 0.4270 |
57
+ | 0.4848 | 0.8475 | 200 | 0.4059 |
58
+
59
+
60
+ ### Framework versions
61
+
62
+ - Transformers 4.46.1
63
+ - Pytorch 2.8.0+cu128
64
+ - Datasets 3.1.0
65
+ - Tokenizers 0.20.3
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_loss": 0.4036284387111664,
4
+ "eval_runtime": 4.9907,
5
+ "eval_samples_per_second": 0.2,
6
+ "eval_steps_per_second": 0.2,
7
+ "total_flos": 11901468672000.0,
8
+ "train_loss": 0.4903946296643403,
9
+ "train_runtime": 2458.2804,
10
+ "train_samples_per_second": 0.383,
11
+ "train_steps_per_second": 0.096
12
+ }
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Llama-3.2-3B-Instruct",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "head_dim": 128,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 3072,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 8192,
19
+ "max_position_embeddings": 131072,
20
+ "mlp_bias": false,
21
+ "model_type": "llama",
22
+ "num_attention_heads": 24,
23
+ "num_hidden_layers": 28,
24
+ "num_key_value_heads": 8,
25
+ "pretraining_tp": 1,
26
+ "rms_norm_eps": 1e-05,
27
+ "rope_scaling": {
28
+ "factor": 32.0,
29
+ "high_freq_factor": 4.0,
30
+ "low_freq_factor": 1.0,
31
+ "original_max_position_embeddings": 8192,
32
+ "rope_type": "llama3"
33
+ },
34
+ "rope_theta": 500000.0,
35
+ "tie_word_embeddings": true,
36
+ "torch_dtype": "bfloat16",
37
+ "transformers_version": "4.46.1",
38
+ "use_cache": false,
39
+ "vocab_size": 128256
40
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_loss": 0.4036284387111664,
4
+ "eval_runtime": 4.9907,
5
+ "eval_samples_per_second": 0.2,
6
+ "eval_steps_per_second": 0.2
7
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.46.1"
12
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cf1eaba0e40f6561368765a1bcdd26dc4ee745a4e85f1320e791895675372b5
3
+ size 4965799096
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a9772cd6561bc3e119983affc7d3217d45ec453211486bcefd3e64c3e4ed9ff
3
+ size 1459729952
model.safetensors.index.json ADDED
@@ -0,0 +1,261 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 6425499648
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
125
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
126
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
129
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
134
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
135
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
136
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
137
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
138
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
139
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
140
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
141
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
142
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
143
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
144
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
145
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
146
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
147
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
148
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
149
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
150
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
151
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
152
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
153
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
154
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
155
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
156
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
157
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
158
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
159
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
160
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
161
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
162
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
163
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
164
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
165
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
166
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
167
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
168
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
169
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
170
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
171
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
172
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
173
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
174
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
175
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
176
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
177
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
178
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
179
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
180
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
181
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
182
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
183
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
184
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
185
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
186
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
187
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
188
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
189
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
190
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
191
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
192
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
193
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
194
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
195
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
196
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
197
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
198
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
199
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
200
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
201
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
202
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
203
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
204
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
205
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
206
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
207
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
208
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
209
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
210
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
211
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
212
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
213
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
214
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
215
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
216
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
217
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
218
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
219
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
220
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
221
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
222
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
223
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
224
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
225
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
226
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
227
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
228
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
229
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
230
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
231
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
232
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
233
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
234
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
235
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
236
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
237
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
238
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
239
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
240
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
241
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
242
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
243
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
244
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
245
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
246
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
247
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
248
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
249
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
250
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
251
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
252
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
253
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
254
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
255
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
256
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
257
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
258
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
259
+ "model.norm.weight": "model-00002-of-00002.safetensors"
260
+ }
261
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|eot_id|>"
17
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
tokenizer_config.json ADDED
@@ -0,0 +1,2065 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {{- \"<|eot_id|>\" }}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 131072,
2061
+ "pad_token": "<|eot_id|>",
2062
+ "padding_side": "right",
2063
+ "split_special_tokens": false,
2064
+ "tokenizer_class": "PreTrainedTokenizerFast"
2065
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 11901468672000.0,
4
+ "train_loss": 0.4903946296643403,
5
+ "train_runtime": 2458.2804,
6
+ "train_samples_per_second": 0.383,
7
+ "train_steps_per_second": 0.096
8
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 1, "total_steps": 236, "loss": 1.2687, "lr": 4.999778497139455e-06, "epoch": 0.00423728813559322, "percentage": 0.42, "elapsed_time": "0:00:14", "remaining_time": "0:57:50"}
2
+ {"current_steps": 2, "total_steps": 236, "loss": 1.0951, "lr": 4.999114027808632e-06, "epoch": 0.00847457627118644, "percentage": 0.85, "elapsed_time": "0:00:25", "remaining_time": "0:49:06"}
3
+ {"current_steps": 3, "total_steps": 236, "loss": 0.9302, "lr": 4.998006709753017e-06, "epoch": 0.012711864406779662, "percentage": 1.27, "elapsed_time": "0:00:35", "remaining_time": "0:45:54"}
4
+ {"current_steps": 4, "total_steps": 236, "loss": 0.9381, "lr": 4.996456739191905e-06, "epoch": 0.01694915254237288, "percentage": 1.69, "elapsed_time": "0:00:45", "remaining_time": "0:44:14"}
5
+ {"current_steps": 5, "total_steps": 236, "loss": 0.8816, "lr": 4.994464390783626e-06, "epoch": 0.0211864406779661, "percentage": 2.12, "elapsed_time": "0:00:56", "remaining_time": "0:43:10"}
6
+ {"current_steps": 6, "total_steps": 236, "loss": 0.929, "lr": 4.992030017576876e-06, "epoch": 0.025423728813559324, "percentage": 2.54, "elapsed_time": "0:01:06", "remaining_time": "0:42:24"}
7
+ {"current_steps": 7, "total_steps": 236, "loss": 0.7506, "lr": 4.989154050948159e-06, "epoch": 0.029661016949152543, "percentage": 2.97, "elapsed_time": "0:01:16", "remaining_time": "0:41:48"}
8
+ {"current_steps": 8, "total_steps": 236, "loss": 0.6705, "lr": 4.9858370005253435e-06, "epoch": 0.03389830508474576, "percentage": 3.39, "elapsed_time": "0:01:27", "remaining_time": "0:41:19"}
9
+ {"current_steps": 9, "total_steps": 236, "loss": 0.6332, "lr": 4.982079454097354e-06, "epoch": 0.038135593220338986, "percentage": 3.81, "elapsed_time": "0:01:37", "remaining_time": "0:40:54"}
10
+ {"current_steps": 10, "total_steps": 236, "loss": 0.653, "lr": 4.977882077510018e-06, "epoch": 0.0423728813559322, "percentage": 4.24, "elapsed_time": "0:01:47", "remaining_time": "0:40:33"}
11
+ {"current_steps": 11, "total_steps": 236, "loss": 0.6429, "lr": 4.9732456145480716e-06, "epoch": 0.046610169491525424, "percentage": 4.66, "elapsed_time": "0:01:58", "remaining_time": "0:40:13"}
12
+ {"current_steps": 12, "total_steps": 236, "loss": 0.599, "lr": 4.968170886803361e-06, "epoch": 0.05084745762711865, "percentage": 5.08, "elapsed_time": "0:02:08", "remaining_time": "0:39:56"}
13
+ {"current_steps": 13, "total_steps": 236, "loss": 0.5596, "lr": 4.962658793529258e-06, "epoch": 0.05508474576271186, "percentage": 5.51, "elapsed_time": "0:02:18", "remaining_time": "0:39:39"}
14
+ {"current_steps": 14, "total_steps": 236, "loss": 0.5753, "lr": 4.956710311481303e-06, "epoch": 0.059322033898305086, "percentage": 5.93, "elapsed_time": "0:02:29", "remaining_time": "0:39:24"}
15
+ {"current_steps": 15, "total_steps": 236, "loss": 0.5945, "lr": 4.950326494744127e-06, "epoch": 0.0635593220338983, "percentage": 6.36, "elapsed_time": "0:02:39", "remaining_time": "0:39:09"}
16
+ {"current_steps": 16, "total_steps": 236, "loss": 0.5558, "lr": 4.943508474544667e-06, "epoch": 0.06779661016949153, "percentage": 6.78, "elapsed_time": "0:02:49", "remaining_time": "0:38:55"}
17
+ {"current_steps": 17, "total_steps": 236, "loss": 0.5743, "lr": 4.936257459051703e-06, "epoch": 0.07203389830508475, "percentage": 7.2, "elapsed_time": "0:03:00", "remaining_time": "0:38:41"}
18
+ {"current_steps": 18, "total_steps": 236, "loss": 0.6069, "lr": 4.928574733161775e-06, "epoch": 0.07627118644067797, "percentage": 7.63, "elapsed_time": "0:03:10", "remaining_time": "0:38:27"}
19
+ {"current_steps": 19, "total_steps": 236, "loss": 0.6191, "lr": 4.920461658271492e-06, "epoch": 0.08050847457627118, "percentage": 8.05, "elapsed_time": "0:03:20", "remaining_time": "0:38:14"}
20
+ {"current_steps": 20, "total_steps": 236, "loss": 0.5708, "lr": 4.911919672036291e-06, "epoch": 0.0847457627118644, "percentage": 8.47, "elapsed_time": "0:03:31", "remaining_time": "0:38:01"}
21
+ {"current_steps": 21, "total_steps": 236, "loss": 0.5543, "lr": 4.902950288115679e-06, "epoch": 0.08898305084745763, "percentage": 8.9, "elapsed_time": "0:03:41", "remaining_time": "0:37:49"}
22
+ {"current_steps": 22, "total_steps": 236, "loss": 0.5413, "lr": 4.8935550959050135e-06, "epoch": 0.09322033898305085, "percentage": 9.32, "elapsed_time": "0:03:51", "remaining_time": "0:37:36"}
23
+ {"current_steps": 23, "total_steps": 236, "loss": 0.5366, "lr": 4.883735760253856e-06, "epoch": 0.09745762711864407, "percentage": 9.75, "elapsed_time": "0:04:02", "remaining_time": "0:37:24"}
24
+ {"current_steps": 24, "total_steps": 236, "loss": 0.5023, "lr": 4.8734940211709535e-06, "epoch": 0.1016949152542373, "percentage": 10.17, "elapsed_time": "0:04:12", "remaining_time": "0:37:11"}
25
+ {"current_steps": 25, "total_steps": 236, "loss": 0.579, "lr": 4.862831693515909e-06, "epoch": 0.1059322033898305, "percentage": 10.59, "elapsed_time": "0:04:23", "remaining_time": "0:36:59"}
26
+ {"current_steps": 26, "total_steps": 236, "loss": 0.5114, "lr": 4.851750666677583e-06, "epoch": 0.11016949152542373, "percentage": 11.02, "elapsed_time": "0:04:33", "remaining_time": "0:36:47"}
27
+ {"current_steps": 27, "total_steps": 236, "loss": 0.501, "lr": 4.840252904239291e-06, "epoch": 0.11440677966101695, "percentage": 11.44, "elapsed_time": "0:04:43", "remaining_time": "0:36:35"}
28
+ {"current_steps": 28, "total_steps": 236, "loss": 0.5558, "lr": 4.828340443630847e-06, "epoch": 0.11864406779661017, "percentage": 11.86, "elapsed_time": "0:04:53", "remaining_time": "0:36:23"}
29
+ {"current_steps": 29, "total_steps": 236, "loss": 0.485, "lr": 4.8160153957675315e-06, "epoch": 0.1228813559322034, "percentage": 12.29, "elapsed_time": "0:05:04", "remaining_time": "0:36:12"}
30
+ {"current_steps": 30, "total_steps": 236, "loss": 0.5526, "lr": 4.8032799446760326e-06, "epoch": 0.1271186440677966, "percentage": 12.71, "elapsed_time": "0:05:14", "remaining_time": "0:36:00"}
31
+ {"current_steps": 31, "total_steps": 236, "loss": 0.5322, "lr": 4.790136347107427e-06, "epoch": 0.13135593220338984, "percentage": 13.14, "elapsed_time": "0:05:24", "remaining_time": "0:35:48"}
32
+ {"current_steps": 32, "total_steps": 236, "loss": 0.4939, "lr": 4.7765869321372835e-06, "epoch": 0.13559322033898305, "percentage": 13.56, "elapsed_time": "0:05:35", "remaining_time": "0:35:36"}
33
+ {"current_steps": 33, "total_steps": 236, "loss": 0.5233, "lr": 4.76263410075294e-06, "epoch": 0.13983050847457626, "percentage": 13.98, "elapsed_time": "0:05:45", "remaining_time": "0:35:25"}
34
+ {"current_steps": 34, "total_steps": 236, "loss": 0.5195, "lr": 4.7482803254280485e-06, "epoch": 0.1440677966101695, "percentage": 14.41, "elapsed_time": "0:05:55", "remaining_time": "0:35:13"}
35
+ {"current_steps": 35, "total_steps": 236, "loss": 0.5188, "lr": 4.733528149684444e-06, "epoch": 0.1483050847457627, "percentage": 14.83, "elapsed_time": "0:06:06", "remaining_time": "0:35:02"}
36
+ {"current_steps": 36, "total_steps": 236, "loss": 0.5102, "lr": 4.718380187641429e-06, "epoch": 0.15254237288135594, "percentage": 15.25, "elapsed_time": "0:06:16", "remaining_time": "0:34:51"}
37
+ {"current_steps": 37, "total_steps": 236, "loss": 0.5413, "lr": 4.7028391235525414e-06, "epoch": 0.15677966101694915, "percentage": 15.68, "elapsed_time": "0:06:26", "remaining_time": "0:34:39"}
38
+ {"current_steps": 38, "total_steps": 236, "loss": 0.503, "lr": 4.686907711329903e-06, "epoch": 0.16101694915254236, "percentage": 16.1, "elapsed_time": "0:06:37", "remaining_time": "0:34:28"}
39
+ {"current_steps": 39, "total_steps": 236, "loss": 0.5292, "lr": 4.670588774056218e-06, "epoch": 0.1652542372881356, "percentage": 16.53, "elapsed_time": "0:06:47", "remaining_time": "0:34:17"}
40
+ {"current_steps": 40, "total_steps": 236, "loss": 0.5267, "lr": 4.653885203484516e-06, "epoch": 0.1694915254237288, "percentage": 16.95, "elapsed_time": "0:06:57", "remaining_time": "0:34:06"}
41
+ {"current_steps": 41, "total_steps": 236, "loss": 0.5156, "lr": 4.636799959525726e-06, "epoch": 0.17372881355932204, "percentage": 17.37, "elapsed_time": "0:07:08", "remaining_time": "0:33:55"}
42
+ {"current_steps": 42, "total_steps": 236, "loss": 0.5199, "lr": 4.619336069724177e-06, "epoch": 0.17796610169491525, "percentage": 17.8, "elapsed_time": "0:07:18", "remaining_time": "0:33:44"}
43
+ {"current_steps": 43, "total_steps": 236, "loss": 0.5106, "lr": 4.601496628721108e-06, "epoch": 0.18220338983050846, "percentage": 18.22, "elapsed_time": "0:07:28", "remaining_time": "0:33:33"}
44
+ {"current_steps": 44, "total_steps": 236, "loss": 0.5057, "lr": 4.583284797706288e-06, "epoch": 0.1864406779661017, "percentage": 18.64, "elapsed_time": "0:07:38", "remaining_time": "0:33:22"}
45
+ {"current_steps": 45, "total_steps": 236, "loss": 0.5035, "lr": 4.564703803857849e-06, "epoch": 0.1906779661016949, "percentage": 19.07, "elapsed_time": "0:07:49", "remaining_time": "0:33:11"}
46
+ {"current_steps": 46, "total_steps": 236, "loss": 0.4671, "lr": 4.5457569397704226e-06, "epoch": 0.19491525423728814, "percentage": 19.49, "elapsed_time": "0:07:59", "remaining_time": "0:33:01"}
47
+ {"current_steps": 47, "total_steps": 236, "loss": 0.4861, "lr": 4.526447562871685e-06, "epoch": 0.19915254237288135, "percentage": 19.92, "elapsed_time": "0:08:09", "remaining_time": "0:32:50"}
48
+ {"current_steps": 48, "total_steps": 236, "loss": 0.5108, "lr": 4.506779094827409e-06, "epoch": 0.2033898305084746, "percentage": 20.34, "elapsed_time": "0:08:20", "remaining_time": "0:32:39"}
49
+ {"current_steps": 49, "total_steps": 236, "loss": 0.4739, "lr": 4.486755020935144e-06, "epoch": 0.2076271186440678, "percentage": 20.76, "elapsed_time": "0:08:30", "remaining_time": "0:32:28"}
50
+ {"current_steps": 50, "total_steps": 236, "loss": 0.4923, "lr": 4.466378889506607e-06, "epoch": 0.211864406779661, "percentage": 21.19, "elapsed_time": "0:08:40", "remaining_time": "0:32:17"}
51
+ {"current_steps": 51, "total_steps": 236, "loss": 0.4691, "lr": 4.445654311238915e-06, "epoch": 0.21610169491525424, "percentage": 21.61, "elapsed_time": "0:08:51", "remaining_time": "0:32:07"}
52
+ {"current_steps": 52, "total_steps": 236, "loss": 0.5078, "lr": 4.424584958574766e-06, "epoch": 0.22033898305084745, "percentage": 22.03, "elapsed_time": "0:09:01", "remaining_time": "0:31:56"}
53
+ {"current_steps": 53, "total_steps": 236, "loss": 0.5286, "lr": 4.403174565051667e-06, "epoch": 0.2245762711864407, "percentage": 22.46, "elapsed_time": "0:09:11", "remaining_time": "0:31:45"}
54
+ {"current_steps": 54, "total_steps": 236, "loss": 0.5144, "lr": 4.381426924640346e-06, "epoch": 0.2288135593220339, "percentage": 22.88, "elapsed_time": "0:09:22", "remaining_time": "0:31:35"}
55
+ {"current_steps": 55, "total_steps": 236, "loss": 0.5053, "lr": 4.359345891072454e-06, "epoch": 0.2330508474576271, "percentage": 23.31, "elapsed_time": "0:09:32", "remaining_time": "0:31:24"}
56
+ {"current_steps": 56, "total_steps": 236, "loss": 0.4833, "lr": 4.336935377157668e-06, "epoch": 0.23728813559322035, "percentage": 23.73, "elapsed_time": "0:09:42", "remaining_time": "0:31:13"}
57
+ {"current_steps": 57, "total_steps": 236, "loss": 0.4854, "lr": 4.31419935409034e-06, "epoch": 0.24152542372881355, "percentage": 24.15, "elapsed_time": "0:09:53", "remaining_time": "0:31:03"}
58
+ {"current_steps": 58, "total_steps": 236, "loss": 0.4768, "lr": 4.291141850745788e-06, "epoch": 0.2457627118644068, "percentage": 24.58, "elapsed_time": "0:10:03", "remaining_time": "0:30:52"}
59
+ {"current_steps": 59, "total_steps": 236, "loss": 0.4731, "lr": 4.267766952966369e-06, "epoch": 0.25, "percentage": 25.0, "elapsed_time": "0:10:13", "remaining_time": "0:30:41"}
60
+ {"current_steps": 60, "total_steps": 236, "loss": 0.4654, "lr": 4.244078802837462e-06, "epoch": 0.2542372881355932, "percentage": 25.42, "elapsed_time": "0:10:24", "remaining_time": "0:30:31"}
61
+ {"current_steps": 61, "total_steps": 236, "loss": 0.4255, "lr": 4.220081597953479e-06, "epoch": 0.2584745762711864, "percentage": 25.85, "elapsed_time": "0:10:34", "remaining_time": "0:30:20"}
62
+ {"current_steps": 62, "total_steps": 236, "loss": 0.4799, "lr": 4.1957795906740404e-06, "epoch": 0.2627118644067797, "percentage": 26.27, "elapsed_time": "0:10:44", "remaining_time": "0:30:10"}
63
+ {"current_steps": 63, "total_steps": 236, "loss": 0.4945, "lr": 4.171177087370452e-06, "epoch": 0.2669491525423729, "percentage": 26.69, "elapsed_time": "0:10:55", "remaining_time": "0:29:59"}
64
+ {"current_steps": 64, "total_steps": 236, "loss": 0.5011, "lr": 4.146278447662597e-06, "epoch": 0.2711864406779661, "percentage": 27.12, "elapsed_time": "0:11:05", "remaining_time": "0:29:48"}
65
+ {"current_steps": 65, "total_steps": 236, "loss": 0.5116, "lr": 4.1210880836464135e-06, "epoch": 0.2754237288135593, "percentage": 27.54, "elapsed_time": "0:11:15", "remaining_time": "0:29:38"}
66
+ {"current_steps": 66, "total_steps": 236, "loss": 0.4816, "lr": 4.095610459112051e-06, "epoch": 0.2796610169491525, "percentage": 27.97, "elapsed_time": "0:11:26", "remaining_time": "0:29:27"}
67
+ {"current_steps": 67, "total_steps": 236, "loss": 0.4783, "lr": 4.06985008875288e-06, "epoch": 0.2838983050847458, "percentage": 28.39, "elapsed_time": "0:11:36", "remaining_time": "0:29:17"}
68
+ {"current_steps": 68, "total_steps": 236, "loss": 0.469, "lr": 4.04381153736548e-06, "epoch": 0.288135593220339, "percentage": 28.81, "elapsed_time": "0:11:46", "remaining_time": "0:29:06"}
69
+ {"current_steps": 69, "total_steps": 236, "loss": 0.4899, "lr": 4.017499419040745e-06, "epoch": 0.2923728813559322, "percentage": 29.24, "elapsed_time": "0:11:57", "remaining_time": "0:28:55"}
70
+ {"current_steps": 70, "total_steps": 236, "loss": 0.466, "lr": 3.990918396346254e-06, "epoch": 0.2966101694915254, "percentage": 29.66, "elapsed_time": "0:12:07", "remaining_time": "0:28:45"}
71
+ {"current_steps": 71, "total_steps": 236, "loss": 0.4554, "lr": 3.964073179500059e-06, "epoch": 0.3008474576271186, "percentage": 30.08, "elapsed_time": "0:12:17", "remaining_time": "0:28:34"}
72
+ {"current_steps": 72, "total_steps": 236, "loss": 0.4309, "lr": 3.936968525536018e-06, "epoch": 0.3050847457627119, "percentage": 30.51, "elapsed_time": "0:12:28", "remaining_time": "0:28:24"}
73
+ {"current_steps": 73, "total_steps": 236, "loss": 0.4544, "lr": 3.90960923746084e-06, "epoch": 0.3093220338983051, "percentage": 30.93, "elapsed_time": "0:12:38", "remaining_time": "0:28:13"}
74
+ {"current_steps": 74, "total_steps": 236, "loss": 0.5207, "lr": 3.882000163402984e-06, "epoch": 0.3135593220338983, "percentage": 31.36, "elapsed_time": "0:12:48", "remaining_time": "0:28:02"}
75
+ {"current_steps": 75, "total_steps": 236, "loss": 0.4715, "lr": 3.854146195753553e-06, "epoch": 0.3177966101694915, "percentage": 31.78, "elapsed_time": "0:12:59", "remaining_time": "0:27:52"}
76
+ {"current_steps": 76, "total_steps": 236, "loss": 0.516, "lr": 3.826052270299356e-06, "epoch": 0.3220338983050847, "percentage": 32.2, "elapsed_time": "0:13:09", "remaining_time": "0:27:41"}
77
+ {"current_steps": 77, "total_steps": 236, "loss": 0.4777, "lr": 3.797723365348277e-06, "epoch": 0.326271186440678, "percentage": 32.63, "elapsed_time": "0:13:19", "remaining_time": "0:27:31"}
78
+ {"current_steps": 78, "total_steps": 236, "loss": 0.4673, "lr": 3.7691645008471e-06, "epoch": 0.3305084745762712, "percentage": 33.05, "elapsed_time": "0:13:30", "remaining_time": "0:27:20"}
79
+ {"current_steps": 79, "total_steps": 236, "loss": 0.4351, "lr": 3.7403807374919717e-06, "epoch": 0.3347457627118644, "percentage": 33.47, "elapsed_time": "0:13:40", "remaining_time": "0:27:10"}
80
+ {"current_steps": 80, "total_steps": 236, "loss": 0.5165, "lr": 3.711377175831626e-06, "epoch": 0.3389830508474576, "percentage": 33.9, "elapsed_time": "0:13:50", "remaining_time": "0:26:59"}
81
+ {"current_steps": 81, "total_steps": 236, "loss": 0.4341, "lr": 3.682158955363564e-06, "epoch": 0.3432203389830508, "percentage": 34.32, "elapsed_time": "0:14:01", "remaining_time": "0:26:49"}
82
+ {"current_steps": 82, "total_steps": 236, "loss": 0.4424, "lr": 3.652731253623315e-06, "epoch": 0.3474576271186441, "percentage": 34.75, "elapsed_time": "0:14:11", "remaining_time": "0:26:38"}
83
+ {"current_steps": 83, "total_steps": 236, "loss": 0.4948, "lr": 3.623099285266972e-06, "epoch": 0.3516949152542373, "percentage": 35.17, "elapsed_time": "0:14:21", "remaining_time": "0:26:28"}
84
+ {"current_steps": 84, "total_steps": 236, "loss": 0.495, "lr": 3.593268301147139e-06, "epoch": 0.3559322033898305, "percentage": 35.59, "elapsed_time": "0:14:32", "remaining_time": "0:26:17"}
85
+ {"current_steps": 85, "total_steps": 236, "loss": 0.4686, "lr": 3.563243587382468e-06, "epoch": 0.3601694915254237, "percentage": 36.02, "elapsed_time": "0:14:42", "remaining_time": "0:26:07"}
86
+ {"current_steps": 86, "total_steps": 236, "loss": 0.4805, "lr": 3.5330304644209456e-06, "epoch": 0.3644067796610169, "percentage": 36.44, "elapsed_time": "0:14:52", "remaining_time": "0:25:57"}
87
+ {"current_steps": 87, "total_steps": 236, "loss": 0.5394, "lr": 3.502634286097104e-06, "epoch": 0.3686440677966102, "percentage": 36.86, "elapsed_time": "0:15:03", "remaining_time": "0:25:46"}
88
+ {"current_steps": 88, "total_steps": 236, "loss": 0.4976, "lr": 3.4720604386833024e-06, "epoch": 0.3728813559322034, "percentage": 37.29, "elapsed_time": "0:15:13", "remaining_time": "0:25:36"}
89
+ {"current_steps": 89, "total_steps": 236, "loss": 0.4087, "lr": 3.4413143399352663e-06, "epoch": 0.3771186440677966, "percentage": 37.71, "elapsed_time": "0:15:23", "remaining_time": "0:25:25"}
90
+ {"current_steps": 90, "total_steps": 236, "loss": 0.4367, "lr": 3.410401438132056e-06, "epoch": 0.3813559322033898, "percentage": 38.14, "elapsed_time": "0:15:33", "remaining_time": "0:25:15"}
91
+ {"current_steps": 91, "total_steps": 236, "loss": 0.4592, "lr": 3.3793272111106125e-06, "epoch": 0.3855932203389831, "percentage": 38.56, "elapsed_time": "0:15:44", "remaining_time": "0:25:04"}
92
+ {"current_steps": 92, "total_steps": 236, "loss": 0.4635, "lr": 3.3480971652950757e-06, "epoch": 0.3898305084745763, "percentage": 38.98, "elapsed_time": "0:15:54", "remaining_time": "0:24:54"}
93
+ {"current_steps": 93, "total_steps": 236, "loss": 0.4847, "lr": 3.316716834721033e-06, "epoch": 0.3940677966101695, "percentage": 39.41, "elapsed_time": "0:16:04", "remaining_time": "0:24:43"}
94
+ {"current_steps": 94, "total_steps": 236, "loss": 0.4568, "lr": 3.2851917800548726e-06, "epoch": 0.3983050847457627, "percentage": 39.83, "elapsed_time": "0:16:15", "remaining_time": "0:24:33"}
95
+ {"current_steps": 95, "total_steps": 236, "loss": 0.5261, "lr": 3.253527587608425e-06, "epoch": 0.4025423728813559, "percentage": 40.25, "elapsed_time": "0:16:25", "remaining_time": "0:24:22"}
96
+ {"current_steps": 96, "total_steps": 236, "loss": 0.4596, "lr": 3.221729868349053e-06, "epoch": 0.4067796610169492, "percentage": 40.68, "elapsed_time": "0:16:35", "remaining_time": "0:24:12"}
97
+ {"current_steps": 97, "total_steps": 236, "loss": 0.4194, "lr": 3.1898042569053767e-06, "epoch": 0.4110169491525424, "percentage": 41.1, "elapsed_time": "0:16:46", "remaining_time": "0:24:02"}
98
+ {"current_steps": 98, "total_steps": 236, "loss": 0.4554, "lr": 3.157756410568803e-06, "epoch": 0.4152542372881356, "percentage": 41.53, "elapsed_time": "0:16:56", "remaining_time": "0:23:51"}
99
+ {"current_steps": 99, "total_steps": 236, "loss": 0.6189, "lr": 3.125592008291044e-06, "epoch": 0.4194915254237288, "percentage": 41.95, "elapsed_time": "0:17:07", "remaining_time": "0:23:41"}
100
+ {"current_steps": 100, "total_steps": 236, "loss": 0.5004, "lr": 3.093316749677788e-06, "epoch": 0.423728813559322, "percentage": 42.37, "elapsed_time": "0:17:17", "remaining_time": "0:23:30"}
101
+ {"current_steps": 100, "total_steps": 236, "eval_loss": 0.4270476698875427, "epoch": 0.423728813559322, "percentage": 42.37, "elapsed_time": "0:17:22", "remaining_time": "0:23:38"}
102
+ {"current_steps": 101, "total_steps": 236, "loss": 0.4709, "lr": 3.0609363539787206e-06, "epoch": 0.4279661016949153, "percentage": 42.8, "elapsed_time": "0:17:32", "remaining_time": "0:23:27"}
103
+ {"current_steps": 102, "total_steps": 236, "loss": 0.4697, "lr": 3.028456559074061e-06, "epoch": 0.4322033898305085, "percentage": 43.22, "elapsed_time": "0:17:43", "remaining_time": "0:23:16"}
104
+ {"current_steps": 103, "total_steps": 236, "loss": 0.4797, "lr": 2.9958831204577948e-06, "epoch": 0.4364406779661017, "percentage": 43.64, "elapsed_time": "0:17:53", "remaining_time": "0:23:06"}
105
+ {"current_steps": 104, "total_steps": 236, "loss": 0.4747, "lr": 2.963221810217786e-06, "epoch": 0.4406779661016949, "percentage": 44.07, "elapsed_time": "0:18:03", "remaining_time": "0:22:55"}
106
+ {"current_steps": 105, "total_steps": 236, "loss": 0.4507, "lr": 2.9304784160129535e-06, "epoch": 0.4449152542372881, "percentage": 44.49, "elapsed_time": "0:18:14", "remaining_time": "0:22:45"}
107
+ {"current_steps": 106, "total_steps": 236, "loss": 0.4918, "lr": 2.8976587400476804e-06, "epoch": 0.4491525423728814, "percentage": 44.92, "elapsed_time": "0:18:24", "remaining_time": "0:22:34"}
108
+ {"current_steps": 107, "total_steps": 236, "loss": 0.4457, "lr": 2.8647685980436547e-06, "epoch": 0.4533898305084746, "percentage": 45.34, "elapsed_time": "0:18:34", "remaining_time": "0:22:24"}
109
+ {"current_steps": 108, "total_steps": 236, "loss": 0.4484, "lr": 2.8318138182093053e-06, "epoch": 0.4576271186440678, "percentage": 45.76, "elapsed_time": "0:18:45", "remaining_time": "0:22:13"}
110
+ {"current_steps": 109, "total_steps": 236, "loss": 0.5083, "lr": 2.7988002402070346e-06, "epoch": 0.461864406779661, "percentage": 46.19, "elapsed_time": "0:18:55", "remaining_time": "0:22:02"}
111
+ {"current_steps": 110, "total_steps": 236, "loss": 0.4645, "lr": 2.7657337141184137e-06, "epoch": 0.4661016949152542, "percentage": 46.61, "elapsed_time": "0:19:05", "remaining_time": "0:21:52"}
112
+ {"current_steps": 111, "total_steps": 236, "loss": 0.5214, "lr": 2.7326200994075364e-06, "epoch": 0.4703389830508475, "percentage": 47.03, "elapsed_time": "0:19:16", "remaining_time": "0:21:41"}
113
+ {"current_steps": 112, "total_steps": 236, "loss": 0.4336, "lr": 2.699465263882708e-06, "epoch": 0.4745762711864407, "percentage": 47.46, "elapsed_time": "0:19:26", "remaining_time": "0:21:31"}
114
+ {"current_steps": 113, "total_steps": 236, "loss": 0.4566, "lr": 2.666275082656656e-06, "epoch": 0.4788135593220339, "percentage": 47.88, "elapsed_time": "0:19:36", "remaining_time": "0:21:20"}
115
+ {"current_steps": 114, "total_steps": 236, "loss": 0.467, "lr": 2.6330554371054466e-06, "epoch": 0.4830508474576271, "percentage": 48.31, "elapsed_time": "0:19:47", "remaining_time": "0:21:10"}
116
+ {"current_steps": 115, "total_steps": 236, "loss": 0.4492, "lr": 2.5998122138262944e-06, "epoch": 0.4872881355932203, "percentage": 48.73, "elapsed_time": "0:19:57", "remaining_time": "0:20:59"}
117
+ {"current_steps": 116, "total_steps": 236, "loss": 0.4699, "lr": 2.5665513035944373e-06, "epoch": 0.4915254237288136, "percentage": 49.15, "elapsed_time": "0:20:07", "remaining_time": "0:20:49"}
118
+ {"current_steps": 117, "total_steps": 236, "loss": 0.4227, "lr": 2.533278600319285e-06, "epoch": 0.4957627118644068, "percentage": 49.58, "elapsed_time": "0:20:18", "remaining_time": "0:20:38"}
119
+ {"current_steps": 118, "total_steps": 236, "loss": 0.4425, "lr": 2.5e-06, "epoch": 0.5, "percentage": 50.0, "elapsed_time": "0:20:28", "remaining_time": "0:20:28"}
120
+ {"current_steps": 119, "total_steps": 236, "loss": 0.4548, "lr": 2.466721399680716e-06, "epoch": 0.5042372881355932, "percentage": 50.42, "elapsed_time": "0:20:38", "remaining_time": "0:20:17"}
121
+ {"current_steps": 120, "total_steps": 236, "loss": 0.4671, "lr": 2.4334486964055635e-06, "epoch": 0.5084745762711864, "percentage": 50.85, "elapsed_time": "0:20:49", "remaining_time": "0:20:07"}
122
+ {"current_steps": 121, "total_steps": 236, "loss": 0.4492, "lr": 2.400187786173707e-06, "epoch": 0.5127118644067796, "percentage": 51.27, "elapsed_time": "0:20:59", "remaining_time": "0:19:56"}
123
+ {"current_steps": 122, "total_steps": 236, "loss": 0.4836, "lr": 2.3669445628945543e-06, "epoch": 0.5169491525423728, "percentage": 51.69, "elapsed_time": "0:21:09", "remaining_time": "0:19:46"}
124
+ {"current_steps": 123, "total_steps": 236, "loss": 0.459, "lr": 2.3337249173433447e-06, "epoch": 0.5211864406779662, "percentage": 52.12, "elapsed_time": "0:21:20", "remaining_time": "0:19:36"}
125
+ {"current_steps": 124, "total_steps": 236, "loss": 0.4392, "lr": 2.300534736117292e-06, "epoch": 0.5254237288135594, "percentage": 52.54, "elapsed_time": "0:21:30", "remaining_time": "0:19:25"}
126
+ {"current_steps": 125, "total_steps": 236, "loss": 0.4283, "lr": 2.267379900592464e-06, "epoch": 0.5296610169491526, "percentage": 52.97, "elapsed_time": "0:21:40", "remaining_time": "0:19:15"}
127
+ {"current_steps": 126, "total_steps": 236, "loss": 0.4611, "lr": 2.234266285881587e-06, "epoch": 0.5338983050847458, "percentage": 53.39, "elapsed_time": "0:21:51", "remaining_time": "0:19:04"}
128
+ {"current_steps": 127, "total_steps": 236, "loss": 0.432, "lr": 2.201199759792966e-06, "epoch": 0.538135593220339, "percentage": 53.81, "elapsed_time": "0:22:01", "remaining_time": "0:18:54"}
129
+ {"current_steps": 128, "total_steps": 236, "loss": 0.4412, "lr": 2.1681861817906955e-06, "epoch": 0.5423728813559322, "percentage": 54.24, "elapsed_time": "0:22:11", "remaining_time": "0:18:43"}
130
+ {"current_steps": 129, "total_steps": 236, "loss": 0.463, "lr": 2.135231401956346e-06, "epoch": 0.5466101694915254, "percentage": 54.66, "elapsed_time": "0:22:22", "remaining_time": "0:18:33"}
131
+ {"current_steps": 130, "total_steps": 236, "loss": 0.4583, "lr": 2.1023412599523204e-06, "epoch": 0.5508474576271186, "percentage": 55.08, "elapsed_time": "0:22:32", "remaining_time": "0:18:22"}
132
+ {"current_steps": 131, "total_steps": 236, "loss": 0.4451, "lr": 2.069521583987048e-06, "epoch": 0.5550847457627118, "percentage": 55.51, "elapsed_time": "0:22:42", "remaining_time": "0:18:12"}
133
+ {"current_steps": 132, "total_steps": 236, "loss": 0.491, "lr": 2.0367781897822147e-06, "epoch": 0.559322033898305, "percentage": 55.93, "elapsed_time": "0:22:52", "remaining_time": "0:18:01"}
134
+ {"current_steps": 133, "total_steps": 236, "loss": 0.4596, "lr": 2.004116879542205e-06, "epoch": 0.5635593220338984, "percentage": 56.36, "elapsed_time": "0:23:03", "remaining_time": "0:17:51"}
135
+ {"current_steps": 134, "total_steps": 236, "loss": 0.4908, "lr": 1.9715434409259393e-06, "epoch": 0.5677966101694916, "percentage": 56.78, "elapsed_time": "0:23:13", "remaining_time": "0:17:40"}
136
+ {"current_steps": 135, "total_steps": 236, "loss": 0.4634, "lr": 1.9390636460212803e-06, "epoch": 0.5720338983050848, "percentage": 57.2, "elapsed_time": "0:23:23", "remaining_time": "0:17:30"}
137
+ {"current_steps": 136, "total_steps": 236, "loss": 0.4929, "lr": 1.906683250322213e-06, "epoch": 0.576271186440678, "percentage": 57.63, "elapsed_time": "0:23:34", "remaining_time": "0:17:19"}
138
+ {"current_steps": 137, "total_steps": 236, "loss": 0.525, "lr": 1.874407991708957e-06, "epoch": 0.5805084745762712, "percentage": 58.05, "elapsed_time": "0:23:44", "remaining_time": "0:17:09"}
139
+ {"current_steps": 138, "total_steps": 236, "loss": 0.4561, "lr": 1.8422435894311973e-06, "epoch": 0.5847457627118644, "percentage": 58.47, "elapsed_time": "0:23:54", "remaining_time": "0:16:59"}
140
+ {"current_steps": 139, "total_steps": 236, "loss": 0.4868, "lr": 1.8101957430946241e-06, "epoch": 0.5889830508474576, "percentage": 58.9, "elapsed_time": "0:24:05", "remaining_time": "0:16:48"}
141
+ {"current_steps": 140, "total_steps": 236, "loss": 0.4483, "lr": 1.7782701316509482e-06, "epoch": 0.5932203389830508, "percentage": 59.32, "elapsed_time": "0:24:15", "remaining_time": "0:16:38"}
142
+ {"current_steps": 141, "total_steps": 236, "loss": 0.4596, "lr": 1.7464724123915761e-06, "epoch": 0.597457627118644, "percentage": 59.75, "elapsed_time": "0:24:25", "remaining_time": "0:16:27"}
143
+ {"current_steps": 142, "total_steps": 236, "loss": 0.4592, "lr": 1.7148082199451288e-06, "epoch": 0.6016949152542372, "percentage": 60.17, "elapsed_time": "0:24:36", "remaining_time": "0:16:17"}
144
+ {"current_steps": 143, "total_steps": 236, "loss": 0.4581, "lr": 1.6832831652789674e-06, "epoch": 0.6059322033898306, "percentage": 60.59, "elapsed_time": "0:24:46", "remaining_time": "0:16:06"}
145
+ {"current_steps": 144, "total_steps": 236, "loss": 0.4344, "lr": 1.6519028347049242e-06, "epoch": 0.6101694915254238, "percentage": 61.02, "elapsed_time": "0:24:56", "remaining_time": "0:15:56"}
146
+ {"current_steps": 145, "total_steps": 236, "loss": 0.485, "lr": 1.6206727888893875e-06, "epoch": 0.614406779661017, "percentage": 61.44, "elapsed_time": "0:25:07", "remaining_time": "0:15:45"}
147
+ {"current_steps": 146, "total_steps": 236, "loss": 0.4499, "lr": 1.5895985618679447e-06, "epoch": 0.6186440677966102, "percentage": 61.86, "elapsed_time": "0:25:17", "remaining_time": "0:15:35"}
148
+ {"current_steps": 147, "total_steps": 236, "loss": 0.4567, "lr": 1.5586856600647346e-06, "epoch": 0.6228813559322034, "percentage": 62.29, "elapsed_time": "0:25:27", "remaining_time": "0:15:25"}
149
+ {"current_steps": 148, "total_steps": 236, "loss": 0.4706, "lr": 1.5279395613166987e-06, "epoch": 0.6271186440677966, "percentage": 62.71, "elapsed_time": "0:25:38", "remaining_time": "0:15:14"}
150
+ {"current_steps": 149, "total_steps": 236, "loss": 0.4277, "lr": 1.4973657139028963e-06, "epoch": 0.6313559322033898, "percentage": 63.14, "elapsed_time": "0:25:48", "remaining_time": "0:15:04"}
151
+ {"current_steps": 150, "total_steps": 236, "loss": 0.4192, "lr": 1.4669695355790552e-06, "epoch": 0.635593220338983, "percentage": 63.56, "elapsed_time": "0:25:58", "remaining_time": "0:14:53"}
152
+ {"current_steps": 151, "total_steps": 236, "loss": 0.4032, "lr": 1.4367564126175338e-06, "epoch": 0.6398305084745762, "percentage": 63.98, "elapsed_time": "0:26:09", "remaining_time": "0:14:43"}
153
+ {"current_steps": 152, "total_steps": 236, "loss": 0.4176, "lr": 1.4067316988528618e-06, "epoch": 0.6440677966101694, "percentage": 64.41, "elapsed_time": "0:26:19", "remaining_time": "0:14:32"}
154
+ {"current_steps": 153, "total_steps": 236, "loss": 0.4855, "lr": 1.3769007147330282e-06, "epoch": 0.6483050847457628, "percentage": 64.83, "elapsed_time": "0:26:29", "remaining_time": "0:14:22"}
155
+ {"current_steps": 154, "total_steps": 236, "loss": 0.4437, "lr": 1.347268746376685e-06, "epoch": 0.652542372881356, "percentage": 65.25, "elapsed_time": "0:26:40", "remaining_time": "0:14:11"}
156
+ {"current_steps": 155, "total_steps": 236, "loss": 0.4453, "lr": 1.3178410446364376e-06, "epoch": 0.6567796610169492, "percentage": 65.68, "elapsed_time": "0:26:50", "remaining_time": "0:14:01"}
157
+ {"current_steps": 156, "total_steps": 236, "loss": 0.423, "lr": 1.288622824168375e-06, "epoch": 0.6610169491525424, "percentage": 66.1, "elapsed_time": "0:27:00", "remaining_time": "0:13:51"}
158
+ {"current_steps": 157, "total_steps": 236, "loss": 0.465, "lr": 1.2596192625080294e-06, "epoch": 0.6652542372881356, "percentage": 66.53, "elapsed_time": "0:27:11", "remaining_time": "0:13:40"}
159
+ {"current_steps": 158, "total_steps": 236, "loss": 0.477, "lr": 1.230835499152901e-06, "epoch": 0.6694915254237288, "percentage": 66.95, "elapsed_time": "0:27:21", "remaining_time": "0:13:30"}
160
+ {"current_steps": 159, "total_steps": 236, "loss": 0.4747, "lr": 1.202276634651724e-06, "epoch": 0.673728813559322, "percentage": 67.37, "elapsed_time": "0:27:31", "remaining_time": "0:13:19"}
161
+ {"current_steps": 160, "total_steps": 236, "loss": 0.4463, "lr": 1.1739477297006442e-06, "epoch": 0.6779661016949152, "percentage": 67.8, "elapsed_time": "0:27:41", "remaining_time": "0:13:09"}
162
+ {"current_steps": 161, "total_steps": 236, "loss": 0.4314, "lr": 1.1458538042464477e-06, "epoch": 0.6822033898305084, "percentage": 68.22, "elapsed_time": "0:27:52", "remaining_time": "0:12:59"}
163
+ {"current_steps": 162, "total_steps": 236, "loss": 0.4633, "lr": 1.1179998365970174e-06, "epoch": 0.6864406779661016, "percentage": 68.64, "elapsed_time": "0:28:02", "remaining_time": "0:12:48"}
164
+ {"current_steps": 163, "total_steps": 236, "loss": 0.3939, "lr": 1.0903907625391597e-06, "epoch": 0.690677966101695, "percentage": 69.07, "elapsed_time": "0:28:12", "remaining_time": "0:12:38"}
165
+ {"current_steps": 164, "total_steps": 236, "loss": 0.4547, "lr": 1.0630314744639831e-06, "epoch": 0.6949152542372882, "percentage": 69.49, "elapsed_time": "0:28:23", "remaining_time": "0:12:27"}
166
+ {"current_steps": 165, "total_steps": 236, "loss": 0.4544, "lr": 1.0359268204999417e-06, "epoch": 0.6991525423728814, "percentage": 69.92, "elapsed_time": "0:28:33", "remaining_time": "0:12:17"}
167
+ {"current_steps": 166, "total_steps": 236, "loss": 0.4461, "lr": 1.0090816036537462e-06, "epoch": 0.7033898305084746, "percentage": 70.34, "elapsed_time": "0:28:43", "remaining_time": "0:12:06"}
168
+ {"current_steps": 167, "total_steps": 236, "loss": 0.4134, "lr": 9.825005809592565e-07, "epoch": 0.7076271186440678, "percentage": 70.76, "elapsed_time": "0:28:54", "remaining_time": "0:11:56"}
169
+ {"current_steps": 168, "total_steps": 236, "loss": 0.4899, "lr": 9.561884626345206e-07, "epoch": 0.711864406779661, "percentage": 71.19, "elapsed_time": "0:29:04", "remaining_time": "0:11:46"}
170
+ {"current_steps": 169, "total_steps": 236, "loss": 0.4461, "lr": 9.301499112471205e-07, "epoch": 0.7161016949152542, "percentage": 71.61, "elapsed_time": "0:29:14", "remaining_time": "0:11:35"}
171
+ {"current_steps": 170, "total_steps": 236, "loss": 0.4358, "lr": 9.043895408879505e-07, "epoch": 0.7203389830508474, "percentage": 72.03, "elapsed_time": "0:29:25", "remaining_time": "0:11:25"}
172
+ {"current_steps": 171, "total_steps": 236, "loss": 0.443, "lr": 8.789119163535875e-07, "epoch": 0.7245762711864406, "percentage": 72.46, "elapsed_time": "0:29:35", "remaining_time": "0:11:14"}
173
+ {"current_steps": 172, "total_steps": 236, "loss": 0.4332, "lr": 8.537215523374037e-07, "epoch": 0.7288135593220338, "percentage": 72.88, "elapsed_time": "0:29:45", "remaining_time": "0:11:04"}
174
+ {"current_steps": 173, "total_steps": 236, "loss": 0.4423, "lr": 8.288229126295494e-07, "epoch": 0.7330508474576272, "percentage": 73.31, "elapsed_time": "0:29:55", "remaining_time": "0:10:54"}
175
+ {"current_steps": 174, "total_steps": 236, "loss": 0.4513, "lr": 8.042204093259598e-07, "epoch": 0.7372881355932204, "percentage": 73.73, "elapsed_time": "0:30:06", "remaining_time": "0:10:43"}
176
+ {"current_steps": 175, "total_steps": 236, "loss": 0.4446, "lr": 7.799184020465214e-07, "epoch": 0.7415254237288136, "percentage": 74.15, "elapsed_time": "0:30:16", "remaining_time": "0:10:33"}
177
+ {"current_steps": 176, "total_steps": 236, "loss": 0.4516, "lr": 7.559211971625385e-07, "epoch": 0.7457627118644068, "percentage": 74.58, "elapsed_time": "0:30:26", "remaining_time": "0:10:22"}
178
+ {"current_steps": 177, "total_steps": 236, "loss": 0.4226, "lr": 7.322330470336314e-07, "epoch": 0.75, "percentage": 75.0, "elapsed_time": "0:30:37", "remaining_time": "0:10:12"}
179
+ {"current_steps": 178, "total_steps": 236, "loss": 0.4077, "lr": 7.088581492542121e-07, "epoch": 0.7542372881355932, "percentage": 75.42, "elapsed_time": "0:30:47", "remaining_time": "0:10:01"}
180
+ {"current_steps": 179, "total_steps": 236, "loss": 0.4485, "lr": 6.858006459096603e-07, "epoch": 0.7584745762711864, "percentage": 75.85, "elapsed_time": "0:30:57", "remaining_time": "0:09:51"}
181
+ {"current_steps": 180, "total_steps": 236, "loss": 0.4288, "lr": 6.630646228423324e-07, "epoch": 0.7627118644067796, "percentage": 76.27, "elapsed_time": "0:31:08", "remaining_time": "0:09:41"}
182
+ {"current_steps": 181, "total_steps": 236, "loss": 0.4477, "lr": 6.406541089275464e-07, "epoch": 0.7669491525423728, "percentage": 76.69, "elapsed_time": "0:31:18", "remaining_time": "0:09:30"}
183
+ {"current_steps": 182, "total_steps": 236, "loss": 0.4509, "lr": 6.185730753596538e-07, "epoch": 0.7711864406779662, "percentage": 77.12, "elapsed_time": "0:31:28", "remaining_time": "0:09:20"}
184
+ {"current_steps": 183, "total_steps": 236, "loss": 0.4452, "lr": 5.968254349483332e-07, "epoch": 0.7754237288135594, "percentage": 77.54, "elapsed_time": "0:31:39", "remaining_time": "0:09:09"}
185
+ {"current_steps": 184, "total_steps": 236, "loss": 0.456, "lr": 5.754150414252341e-07, "epoch": 0.7796610169491526, "percentage": 77.97, "elapsed_time": "0:31:49", "remaining_time": "0:08:59"}
186
+ {"current_steps": 185, "total_steps": 236, "loss": 0.4866, "lr": 5.543456887610854e-07, "epoch": 0.7838983050847458, "percentage": 78.39, "elapsed_time": "0:31:59", "remaining_time": "0:08:49"}
187
+ {"current_steps": 186, "total_steps": 236, "loss": 0.4635, "lr": 5.336211104933939e-07, "epoch": 0.788135593220339, "percentage": 78.81, "elapsed_time": "0:32:09", "remaining_time": "0:08:38"}
188
+ {"current_steps": 187, "total_steps": 236, "loss": 0.4453, "lr": 5.132449790648561e-07, "epoch": 0.7923728813559322, "percentage": 79.24, "elapsed_time": "0:32:20", "remaining_time": "0:08:28"}
189
+ {"current_steps": 188, "total_steps": 236, "loss": 0.4045, "lr": 4.932209051725915e-07, "epoch": 0.7966101694915254, "percentage": 79.66, "elapsed_time": "0:32:30", "remaining_time": "0:08:18"}
190
+ {"current_steps": 189, "total_steps": 236, "loss": 0.4561, "lr": 4.7355243712831565e-07, "epoch": 0.8008474576271186, "percentage": 80.08, "elapsed_time": "0:32:40", "remaining_time": "0:08:07"}
191
+ {"current_steps": 190, "total_steps": 236, "loss": 0.4603, "lr": 4.542430602295775e-07, "epoch": 0.8050847457627118, "percentage": 80.51, "elapsed_time": "0:32:51", "remaining_time": "0:07:57"}
192
+ {"current_steps": 191, "total_steps": 236, "loss": 0.4428, "lr": 4.3529619614215204e-07, "epoch": 0.809322033898305, "percentage": 80.93, "elapsed_time": "0:33:01", "remaining_time": "0:07:46"}
193
+ {"current_steps": 192, "total_steps": 236, "loss": 0.4501, "lr": 4.167152022937124e-07, "epoch": 0.8135593220338984, "percentage": 81.36, "elapsed_time": "0:33:11", "remaining_time": "0:07:36"}
194
+ {"current_steps": 193, "total_steps": 236, "loss": 0.4503, "lr": 3.9850337127889245e-07, "epoch": 0.8177966101694916, "percentage": 81.78, "elapsed_time": "0:33:22", "remaining_time": "0:07:26"}
195
+ {"current_steps": 194, "total_steps": 236, "loss": 0.5348, "lr": 3.8066393027582276e-07, "epoch": 0.8220338983050848, "percentage": 82.2, "elapsed_time": "0:33:32", "remaining_time": "0:07:15"}
196
+ {"current_steps": 195, "total_steps": 236, "loss": 0.4336, "lr": 3.6320004047427414e-07, "epoch": 0.826271186440678, "percentage": 82.63, "elapsed_time": "0:33:42", "remaining_time": "0:07:05"}
197
+ {"current_steps": 196, "total_steps": 236, "loss": 0.447, "lr": 3.4611479651548456e-07, "epoch": 0.8305084745762712, "percentage": 83.05, "elapsed_time": "0:33:53", "remaining_time": "0:06:54"}
198
+ {"current_steps": 197, "total_steps": 236, "loss": 0.4088, "lr": 3.2941122594378235e-07, "epoch": 0.8347457627118644, "percentage": 83.47, "elapsed_time": "0:34:03", "remaining_time": "0:06:44"}
199
+ {"current_steps": 198, "total_steps": 236, "loss": 0.4462, "lr": 3.130922886700968e-07, "epoch": 0.8389830508474576, "percentage": 83.9, "elapsed_time": "0:34:13", "remaining_time": "0:06:34"}
200
+ {"current_steps": 199, "total_steps": 236, "loss": 0.4717, "lr": 2.9716087644745844e-07, "epoch": 0.8432203389830508, "percentage": 84.32, "elapsed_time": "0:34:24", "remaining_time": "0:06:23"}
201
+ {"current_steps": 200, "total_steps": 236, "loss": 0.4848, "lr": 2.8161981235857145e-07, "epoch": 0.847457627118644, "percentage": 84.75, "elapsed_time": "0:34:34", "remaining_time": "0:06:13"}
202
+ {"current_steps": 200, "total_steps": 236, "eval_loss": 0.40594419836997986, "epoch": 0.847457627118644, "percentage": 84.75, "elapsed_time": "0:34:39", "remaining_time": "0:06:14"}
203
+ {"current_steps": 201, "total_steps": 236, "loss": 0.4712, "lr": 2.664718503155561e-07, "epoch": 0.8516949152542372, "percentage": 85.17, "elapsed_time": "0:34:49", "remaining_time": "0:06:03"}
204
+ {"current_steps": 202, "total_steps": 236, "loss": 0.4493, "lr": 2.517196745719522e-07, "epoch": 0.8559322033898306, "percentage": 85.59, "elapsed_time": "0:35:00", "remaining_time": "0:05:53"}
205
+ {"current_steps": 203, "total_steps": 236, "loss": 0.4505, "lr": 2.3736589924706065e-07, "epoch": 0.8601694915254238, "percentage": 86.02, "elapsed_time": "0:35:10", "remaining_time": "0:05:43"}
206
+ {"current_steps": 204, "total_steps": 236, "loss": 0.4511, "lr": 2.2341306786271695e-07, "epoch": 0.864406779661017, "percentage": 86.44, "elapsed_time": "0:35:20", "remaining_time": "0:05:32"}
207
+ {"current_steps": 205, "total_steps": 236, "loss": 0.4118, "lr": 2.098636528925732e-07, "epoch": 0.8686440677966102, "percentage": 86.86, "elapsed_time": "0:35:31", "remaining_time": "0:05:22"}
208
+ {"current_steps": 206, "total_steps": 236, "loss": 0.5221, "lr": 1.967200553239676e-07, "epoch": 0.8728813559322034, "percentage": 87.29, "elapsed_time": "0:35:41", "remaining_time": "0:05:11"}
209
+ {"current_steps": 207, "total_steps": 236, "loss": 0.4514, "lr": 1.839846042324686e-07, "epoch": 0.8771186440677966, "percentage": 87.71, "elapsed_time": "0:35:51", "remaining_time": "0:05:01"}
210
+ {"current_steps": 208, "total_steps": 236, "loss": 0.4854, "lr": 1.7165955636915395e-07, "epoch": 0.8813559322033898, "percentage": 88.14, "elapsed_time": "0:36:02", "remaining_time": "0:04:51"}
211
+ {"current_steps": 209, "total_steps": 236, "loss": 0.4445, "lr": 1.5974709576071e-07, "epoch": 0.885593220338983, "percentage": 88.56, "elapsed_time": "0:36:12", "remaining_time": "0:04:40"}
212
+ {"current_steps": 210, "total_steps": 236, "loss": 0.4384, "lr": 1.4824933332241693e-07, "epoch": 0.8898305084745762, "percentage": 88.98, "elapsed_time": "0:36:22", "remaining_time": "0:04:30"}
213
+ {"current_steps": 211, "total_steps": 236, "loss": 0.4244, "lr": 1.371683064840912e-07, "epoch": 0.8940677966101694, "percentage": 89.41, "elapsed_time": "0:36:33", "remaining_time": "0:04:19"}
214
+ {"current_steps": 212, "total_steps": 236, "loss": 0.4532, "lr": 1.265059788290468e-07, "epoch": 0.8983050847457628, "percentage": 89.83, "elapsed_time": "0:36:43", "remaining_time": "0:04:09"}
215
+ {"current_steps": 213, "total_steps": 236, "loss": 0.4366, "lr": 1.1626423974614414e-07, "epoch": 0.902542372881356, "percentage": 90.25, "elapsed_time": "0:36:53", "remaining_time": "0:03:59"}
216
+ {"current_steps": 214, "total_steps": 236, "loss": 0.4623, "lr": 1.0644490409498636e-07, "epoch": 0.9067796610169492, "percentage": 90.68, "elapsed_time": "0:37:04", "remaining_time": "0:03:48"}
217
+ {"current_steps": 215, "total_steps": 236, "loss": 0.435, "lr": 9.704971188432166e-08, "epoch": 0.9110169491525424, "percentage": 91.1, "elapsed_time": "0:37:14", "remaining_time": "0:03:38"}
218
+ {"current_steps": 216, "total_steps": 236, "loss": 0.4256, "lr": 8.808032796371019e-08, "epoch": 0.9152542372881356, "percentage": 91.53, "elapsed_time": "0:37:24", "remaining_time": "0:03:27"}
219
+ {"current_steps": 217, "total_steps": 236, "loss": 0.5039, "lr": 7.953834172850866e-08, "epoch": 0.9194915254237288, "percentage": 91.95, "elapsed_time": "0:37:35", "remaining_time": "0:03:17"}
220
+ {"current_steps": 218, "total_steps": 236, "loss": 0.4554, "lr": 7.142526683822537e-08, "epoch": 0.923728813559322, "percentage": 92.37, "elapsed_time": "0:37:45", "remaining_time": "0:03:07"}
221
+ {"current_steps": 219, "total_steps": 236, "loss": 0.4183, "lr": 6.374254094829723e-08, "epoch": 0.9279661016949152, "percentage": 92.8, "elapsed_time": "0:37:55", "remaining_time": "0:02:56"}
222
+ {"current_steps": 220, "total_steps": 236, "loss": 0.4348, "lr": 5.649152545533332e-08, "epoch": 0.9322033898305084, "percentage": 93.22, "elapsed_time": "0:38:06", "remaining_time": "0:02:46"}
223
+ {"current_steps": 221, "total_steps": 236, "loss": 0.4161, "lr": 4.967350525587305e-08, "epoch": 0.9364406779661016, "percentage": 93.64, "elapsed_time": "0:38:16", "remaining_time": "0:02:35"}
224
+ {"current_steps": 222, "total_steps": 236, "loss": 0.4828, "lr": 4.328968851869758e-08, "epoch": 0.940677966101695, "percentage": 94.07, "elapsed_time": "0:38:26", "remaining_time": "0:02:25"}
225
+ {"current_steps": 223, "total_steps": 236, "loss": 0.464, "lr": 3.7341206470742355e-08, "epoch": 0.9449152542372882, "percentage": 94.49, "elapsed_time": "0:38:36", "remaining_time": "0:02:15"}
226
+ {"current_steps": 224, "total_steps": 236, "loss": 0.46, "lr": 3.182911319663862e-08, "epoch": 0.9491525423728814, "percentage": 94.92, "elapsed_time": "0:38:47", "remaining_time": "0:02:04"}
227
+ {"current_steps": 225, "total_steps": 236, "loss": 0.4428, "lr": 2.6754385451928655e-08, "epoch": 0.9533898305084746, "percentage": 95.34, "elapsed_time": "0:38:57", "remaining_time": "0:01:54"}
228
+ {"current_steps": 226, "total_steps": 236, "loss": 0.4226, "lr": 2.211792248998229e-08, "epoch": 0.9576271186440678, "percentage": 95.76, "elapsed_time": "0:39:07", "remaining_time": "0:01:43"}
229
+ {"current_steps": 227, "total_steps": 236, "loss": 0.4297, "lr": 1.7920545902646026e-08, "epoch": 0.961864406779661, "percentage": 96.19, "elapsed_time": "0:39:18", "remaining_time": "0:01:33"}
230
+ {"current_steps": 228, "total_steps": 236, "loss": 0.4597, "lr": 1.4162999474657268e-08, "epoch": 0.9661016949152542, "percentage": 96.61, "elapsed_time": "0:39:28", "remaining_time": "0:01:23"}
231
+ {"current_steps": 229, "total_steps": 236, "loss": 0.4038, "lr": 1.0845949051841442e-08, "epoch": 0.9703389830508474, "percentage": 97.03, "elapsed_time": "0:39:38", "remaining_time": "0:01:12"}
232
+ {"current_steps": 230, "total_steps": 236, "loss": 0.4555, "lr": 7.96998242312469e-09, "epoch": 0.9745762711864406, "percentage": 97.46, "elapsed_time": "0:39:49", "remaining_time": "0:01:02"}
233
+ {"current_steps": 231, "total_steps": 236, "loss": 0.4401, "lr": 5.535609216374971e-09, "epoch": 0.9788135593220338, "percentage": 97.88, "elapsed_time": "0:39:59", "remaining_time": "0:00:51"}
234
+ {"current_steps": 232, "total_steps": 236, "loss": 0.4276, "lr": 3.5432608080951392e-09, "epoch": 0.9830508474576272, "percentage": 98.31, "elapsed_time": "0:40:09", "remaining_time": "0:00:41"}
235
+ {"current_steps": 233, "total_steps": 236, "loss": 0.4418, "lr": 1.9932902469829707e-09, "epoch": 0.9872881355932204, "percentage": 98.73, "elapsed_time": "0:40:20", "remaining_time": "0:00:31"}
236
+ {"current_steps": 234, "total_steps": 236, "loss": 0.4684, "lr": 8.859721913684339e-10, "epoch": 0.9915254237288136, "percentage": 99.15, "elapsed_time": "0:40:30", "remaining_time": "0:00:20"}
237
+ {"current_steps": 235, "total_steps": 236, "loss": 0.4722, "lr": 2.2150286054567482e-10, "epoch": 0.9957627118644068, "percentage": 99.58, "elapsed_time": "0:40:40", "remaining_time": "0:00:10"}
238
+ {"current_steps": 236, "total_steps": 236, "loss": 0.4229, "lr": 0.0, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:40:47", "remaining_time": "0:00:00"}
239
+ {"current_steps": 236, "total_steps": 236, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:40:58", "remaining_time": "0:00:00"}
trainer_state.json ADDED
@@ -0,0 +1,1710 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 100,
6
+ "global_step": 236,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.00423728813559322,
13
+ "grad_norm": 24.983636272308356,
14
+ "learning_rate": 4.999778497139455e-06,
15
+ "loss": 1.2687,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.00847457627118644,
20
+ "grad_norm": 14.415471191564915,
21
+ "learning_rate": 4.999114027808632e-06,
22
+ "loss": 1.0951,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.012711864406779662,
27
+ "grad_norm": 5.875151104448685,
28
+ "learning_rate": 4.998006709753017e-06,
29
+ "loss": 0.9302,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.01694915254237288,
34
+ "grad_norm": 5.642021145705149,
35
+ "learning_rate": 4.996456739191905e-06,
36
+ "loss": 0.9381,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.0211864406779661,
41
+ "grad_norm": 5.650397976221686,
42
+ "learning_rate": 4.994464390783626e-06,
43
+ "loss": 0.8816,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.025423728813559324,
48
+ "grad_norm": 7.027654280950954,
49
+ "learning_rate": 4.992030017576876e-06,
50
+ "loss": 0.929,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.029661016949152543,
55
+ "grad_norm": 3.5898222656388676,
56
+ "learning_rate": 4.989154050948159e-06,
57
+ "loss": 0.7506,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.03389830508474576,
62
+ "grad_norm": 2.792456531017606,
63
+ "learning_rate": 4.9858370005253435e-06,
64
+ "loss": 0.6705,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.038135593220338986,
69
+ "grad_norm": 2.6214179279798215,
70
+ "learning_rate": 4.982079454097354e-06,
71
+ "loss": 0.6332,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.0423728813559322,
76
+ "grad_norm": 2.7902036998331097,
77
+ "learning_rate": 4.977882077510018e-06,
78
+ "loss": 0.653,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.046610169491525424,
83
+ "grad_norm": 2.2669201564614667,
84
+ "learning_rate": 4.9732456145480716e-06,
85
+ "loss": 0.6429,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.05084745762711865,
90
+ "grad_norm": 2.255244111965327,
91
+ "learning_rate": 4.968170886803361e-06,
92
+ "loss": 0.599,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.05508474576271186,
97
+ "grad_norm": 2.2437269206522474,
98
+ "learning_rate": 4.962658793529258e-06,
99
+ "loss": 0.5596,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.059322033898305086,
104
+ "grad_norm": 1.8093596583481388,
105
+ "learning_rate": 4.956710311481303e-06,
106
+ "loss": 0.5753,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.0635593220338983,
111
+ "grad_norm": 2.0840115447445053,
112
+ "learning_rate": 4.950326494744127e-06,
113
+ "loss": 0.5945,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.06779661016949153,
118
+ "grad_norm": 2.293613110658051,
119
+ "learning_rate": 4.943508474544667e-06,
120
+ "loss": 0.5558,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.07203389830508475,
125
+ "grad_norm": 2.290868914929294,
126
+ "learning_rate": 4.936257459051703e-06,
127
+ "loss": 0.5743,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.07627118644067797,
132
+ "grad_norm": 2.031003966246651,
133
+ "learning_rate": 4.928574733161775e-06,
134
+ "loss": 0.6069,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.08050847457627118,
139
+ "grad_norm": 2.7029364194547725,
140
+ "learning_rate": 4.920461658271492e-06,
141
+ "loss": 0.6191,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.0847457627118644,
146
+ "grad_norm": 2.0470389374955817,
147
+ "learning_rate": 4.911919672036291e-06,
148
+ "loss": 0.5708,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.08898305084745763,
153
+ "grad_norm": 2.12112364403085,
154
+ "learning_rate": 4.902950288115679e-06,
155
+ "loss": 0.5543,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.09322033898305085,
160
+ "grad_norm": 1.8115995206346756,
161
+ "learning_rate": 4.8935550959050135e-06,
162
+ "loss": 0.5413,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.09745762711864407,
167
+ "grad_norm": 1.8155021373534483,
168
+ "learning_rate": 4.883735760253856e-06,
169
+ "loss": 0.5366,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.1016949152542373,
174
+ "grad_norm": 1.9815668715349637,
175
+ "learning_rate": 4.8734940211709535e-06,
176
+ "loss": 0.5023,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.1059322033898305,
181
+ "grad_norm": 1.8185662457972662,
182
+ "learning_rate": 4.862831693515909e-06,
183
+ "loss": 0.579,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.11016949152542373,
188
+ "grad_norm": 1.917350259967266,
189
+ "learning_rate": 4.851750666677583e-06,
190
+ "loss": 0.5114,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.11440677966101695,
195
+ "grad_norm": 1.7019500305846775,
196
+ "learning_rate": 4.840252904239291e-06,
197
+ "loss": 0.501,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.11864406779661017,
202
+ "grad_norm": 1.8841699951557118,
203
+ "learning_rate": 4.828340443630847e-06,
204
+ "loss": 0.5558,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.1228813559322034,
209
+ "grad_norm": 1.6490118915519663,
210
+ "learning_rate": 4.8160153957675315e-06,
211
+ "loss": 0.485,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.1271186440677966,
216
+ "grad_norm": 1.7341206091023658,
217
+ "learning_rate": 4.8032799446760326e-06,
218
+ "loss": 0.5526,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.13135593220338984,
223
+ "grad_norm": 1.8467555953749002,
224
+ "learning_rate": 4.790136347107427e-06,
225
+ "loss": 0.5322,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.13559322033898305,
230
+ "grad_norm": 1.5832081003883602,
231
+ "learning_rate": 4.7765869321372835e-06,
232
+ "loss": 0.4939,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.13983050847457626,
237
+ "grad_norm": 1.6537616630601975,
238
+ "learning_rate": 4.76263410075294e-06,
239
+ "loss": 0.5233,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.1440677966101695,
244
+ "grad_norm": 1.738262102405704,
245
+ "learning_rate": 4.7482803254280485e-06,
246
+ "loss": 0.5195,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.1483050847457627,
251
+ "grad_norm": 1.5426979355106012,
252
+ "learning_rate": 4.733528149684444e-06,
253
+ "loss": 0.5188,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.15254237288135594,
258
+ "grad_norm": 1.6087829593043768,
259
+ "learning_rate": 4.718380187641429e-06,
260
+ "loss": 0.5102,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.15677966101694915,
265
+ "grad_norm": 1.5635843358226615,
266
+ "learning_rate": 4.7028391235525414e-06,
267
+ "loss": 0.5413,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.16101694915254236,
272
+ "grad_norm": 1.6093959597165723,
273
+ "learning_rate": 4.686907711329903e-06,
274
+ "loss": 0.503,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.1652542372881356,
279
+ "grad_norm": 1.6888344623368943,
280
+ "learning_rate": 4.670588774056218e-06,
281
+ "loss": 0.5292,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.1694915254237288,
286
+ "grad_norm": 1.608184493948994,
287
+ "learning_rate": 4.653885203484516e-06,
288
+ "loss": 0.5267,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.17372881355932204,
293
+ "grad_norm": 1.7129926098802244,
294
+ "learning_rate": 4.636799959525726e-06,
295
+ "loss": 0.5156,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.17796610169491525,
300
+ "grad_norm": 1.6263108073916899,
301
+ "learning_rate": 4.619336069724177e-06,
302
+ "loss": 0.5199,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.18220338983050846,
307
+ "grad_norm": 2.0470119897016947,
308
+ "learning_rate": 4.601496628721108e-06,
309
+ "loss": 0.5106,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.1864406779661017,
314
+ "grad_norm": 1.7395473901075311,
315
+ "learning_rate": 4.583284797706288e-06,
316
+ "loss": 0.5057,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.1906779661016949,
321
+ "grad_norm": 1.7022748302976163,
322
+ "learning_rate": 4.564703803857849e-06,
323
+ "loss": 0.5035,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.19491525423728814,
328
+ "grad_norm": 1.527309369299825,
329
+ "learning_rate": 4.5457569397704226e-06,
330
+ "loss": 0.4671,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.19915254237288135,
335
+ "grad_norm": 1.6077326015491673,
336
+ "learning_rate": 4.526447562871685e-06,
337
+ "loss": 0.4861,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.2033898305084746,
342
+ "grad_norm": 1.9361875890027545,
343
+ "learning_rate": 4.506779094827409e-06,
344
+ "loss": 0.5108,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.2076271186440678,
349
+ "grad_norm": 1.499834611421209,
350
+ "learning_rate": 4.486755020935144e-06,
351
+ "loss": 0.4739,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.211864406779661,
356
+ "grad_norm": 1.6195647320197375,
357
+ "learning_rate": 4.466378889506607e-06,
358
+ "loss": 0.4923,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.21610169491525424,
363
+ "grad_norm": 1.5311662236684391,
364
+ "learning_rate": 4.445654311238915e-06,
365
+ "loss": 0.4691,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.22033898305084745,
370
+ "grad_norm": 1.665739209150479,
371
+ "learning_rate": 4.424584958574766e-06,
372
+ "loss": 0.5078,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.2245762711864407,
377
+ "grad_norm": 1.6811326126972546,
378
+ "learning_rate": 4.403174565051667e-06,
379
+ "loss": 0.5286,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.2288135593220339,
384
+ "grad_norm": 1.881877485941652,
385
+ "learning_rate": 4.381426924640346e-06,
386
+ "loss": 0.5144,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.2330508474576271,
391
+ "grad_norm": 1.5412723515584492,
392
+ "learning_rate": 4.359345891072454e-06,
393
+ "loss": 0.5053,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.23728813559322035,
398
+ "grad_norm": 1.4610304311798663,
399
+ "learning_rate": 4.336935377157668e-06,
400
+ "loss": 0.4833,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.24152542372881355,
405
+ "grad_norm": 1.5311876700525044,
406
+ "learning_rate": 4.31419935409034e-06,
407
+ "loss": 0.4854,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.2457627118644068,
412
+ "grad_norm": 1.460438898162903,
413
+ "learning_rate": 4.291141850745788e-06,
414
+ "loss": 0.4768,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.25,
419
+ "grad_norm": 1.411100136410473,
420
+ "learning_rate": 4.267766952966369e-06,
421
+ "loss": 0.4731,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.2542372881355932,
426
+ "grad_norm": 1.703735375076507,
427
+ "learning_rate": 4.244078802837462e-06,
428
+ "loss": 0.4654,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.2584745762711864,
433
+ "grad_norm": 1.6314648972051569,
434
+ "learning_rate": 4.220081597953479e-06,
435
+ "loss": 0.4255,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.2627118644067797,
440
+ "grad_norm": 1.5875518733355318,
441
+ "learning_rate": 4.1957795906740404e-06,
442
+ "loss": 0.4799,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.2669491525423729,
447
+ "grad_norm": 1.646283854532202,
448
+ "learning_rate": 4.171177087370452e-06,
449
+ "loss": 0.4945,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.2711864406779661,
454
+ "grad_norm": 1.565329035038957,
455
+ "learning_rate": 4.146278447662597e-06,
456
+ "loss": 0.5011,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.2754237288135593,
461
+ "grad_norm": 1.6995741920887437,
462
+ "learning_rate": 4.1210880836464135e-06,
463
+ "loss": 0.5116,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.2796610169491525,
468
+ "grad_norm": 1.5235285600402282,
469
+ "learning_rate": 4.095610459112051e-06,
470
+ "loss": 0.4816,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.2838983050847458,
475
+ "grad_norm": 1.5823875320971696,
476
+ "learning_rate": 4.06985008875288e-06,
477
+ "loss": 0.4783,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.288135593220339,
482
+ "grad_norm": 1.6905213883969465,
483
+ "learning_rate": 4.04381153736548e-06,
484
+ "loss": 0.469,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.2923728813559322,
489
+ "grad_norm": 1.5203775863207916,
490
+ "learning_rate": 4.017499419040745e-06,
491
+ "loss": 0.4899,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.2966101694915254,
496
+ "grad_norm": 1.4412177109203772,
497
+ "learning_rate": 3.990918396346254e-06,
498
+ "loss": 0.466,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.3008474576271186,
503
+ "grad_norm": 1.423198771775028,
504
+ "learning_rate": 3.964073179500059e-06,
505
+ "loss": 0.4554,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.3050847457627119,
510
+ "grad_norm": 1.478730930392583,
511
+ "learning_rate": 3.936968525536018e-06,
512
+ "loss": 0.4309,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.3093220338983051,
517
+ "grad_norm": 1.4035840623237712,
518
+ "learning_rate": 3.90960923746084e-06,
519
+ "loss": 0.4544,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.3135593220338983,
524
+ "grad_norm": 1.8429355748011418,
525
+ "learning_rate": 3.882000163402984e-06,
526
+ "loss": 0.5207,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.3177966101694915,
531
+ "grad_norm": 1.5918974576626501,
532
+ "learning_rate": 3.854146195753553e-06,
533
+ "loss": 0.4715,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.3220338983050847,
538
+ "grad_norm": 1.6856632648491257,
539
+ "learning_rate": 3.826052270299356e-06,
540
+ "loss": 0.516,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.326271186440678,
545
+ "grad_norm": 1.566736210958077,
546
+ "learning_rate": 3.797723365348277e-06,
547
+ "loss": 0.4777,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.3305084745762712,
552
+ "grad_norm": 1.4733948849435599,
553
+ "learning_rate": 3.7691645008471e-06,
554
+ "loss": 0.4673,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.3347457627118644,
559
+ "grad_norm": 1.4649226412374687,
560
+ "learning_rate": 3.7403807374919717e-06,
561
+ "loss": 0.4351,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.3389830508474576,
566
+ "grad_norm": 4.186726318769653,
567
+ "learning_rate": 3.711377175831626e-06,
568
+ "loss": 0.5165,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.3432203389830508,
573
+ "grad_norm": 1.4759221697182707,
574
+ "learning_rate": 3.682158955363564e-06,
575
+ "loss": 0.4341,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.3474576271186441,
580
+ "grad_norm": 1.4547695340067244,
581
+ "learning_rate": 3.652731253623315e-06,
582
+ "loss": 0.4424,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.3516949152542373,
587
+ "grad_norm": 1.5953206735184406,
588
+ "learning_rate": 3.623099285266972e-06,
589
+ "loss": 0.4948,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.3559322033898305,
594
+ "grad_norm": 1.6232494680819791,
595
+ "learning_rate": 3.593268301147139e-06,
596
+ "loss": 0.495,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.3601694915254237,
601
+ "grad_norm": 1.517925464683624,
602
+ "learning_rate": 3.563243587382468e-06,
603
+ "loss": 0.4686,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.3644067796610169,
608
+ "grad_norm": 1.4281449367937558,
609
+ "learning_rate": 3.5330304644209456e-06,
610
+ "loss": 0.4805,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.3686440677966102,
615
+ "grad_norm": 1.6707175902285467,
616
+ "learning_rate": 3.502634286097104e-06,
617
+ "loss": 0.5394,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.3728813559322034,
622
+ "grad_norm": 1.4655259548590436,
623
+ "learning_rate": 3.4720604386833024e-06,
624
+ "loss": 0.4976,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.3771186440677966,
629
+ "grad_norm": 1.3474366662865283,
630
+ "learning_rate": 3.4413143399352663e-06,
631
+ "loss": 0.4087,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.3813559322033898,
636
+ "grad_norm": 1.3424749954725053,
637
+ "learning_rate": 3.410401438132056e-06,
638
+ "loss": 0.4367,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.3855932203389831,
643
+ "grad_norm": 1.4743384865473754,
644
+ "learning_rate": 3.3793272111106125e-06,
645
+ "loss": 0.4592,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.3898305084745763,
650
+ "grad_norm": 1.641579216938211,
651
+ "learning_rate": 3.3480971652950757e-06,
652
+ "loss": 0.4635,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.3940677966101695,
657
+ "grad_norm": 1.5325003114677715,
658
+ "learning_rate": 3.316716834721033e-06,
659
+ "loss": 0.4847,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.3983050847457627,
664
+ "grad_norm": 1.4417019954799954,
665
+ "learning_rate": 3.2851917800548726e-06,
666
+ "loss": 0.4568,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.4025423728813559,
671
+ "grad_norm": 2.4115242107037216,
672
+ "learning_rate": 3.253527587608425e-06,
673
+ "loss": 0.5261,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.4067796610169492,
678
+ "grad_norm": 1.4550347024666652,
679
+ "learning_rate": 3.221729868349053e-06,
680
+ "loss": 0.4596,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.4110169491525424,
685
+ "grad_norm": 1.4249515222766969,
686
+ "learning_rate": 3.1898042569053767e-06,
687
+ "loss": 0.4194,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.4152542372881356,
692
+ "grad_norm": 1.4701138374466385,
693
+ "learning_rate": 3.157756410568803e-06,
694
+ "loss": 0.4554,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.4194915254237288,
699
+ "grad_norm": 1.8762173298734097,
700
+ "learning_rate": 3.125592008291044e-06,
701
+ "loss": 0.6189,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.423728813559322,
706
+ "grad_norm": 2.207657565751068,
707
+ "learning_rate": 3.093316749677788e-06,
708
+ "loss": 0.5004,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.423728813559322,
713
+ "eval_loss": 0.4270476698875427,
714
+ "eval_runtime": 5.3482,
715
+ "eval_samples_per_second": 0.187,
716
+ "eval_steps_per_second": 0.187,
717
+ "step": 100
718
+ },
719
+ {
720
+ "epoch": 0.4279661016949153,
721
+ "grad_norm": 1.5832081956003763,
722
+ "learning_rate": 3.0609363539787206e-06,
723
+ "loss": 0.4709,
724
+ "step": 101
725
+ },
726
+ {
727
+ "epoch": 0.4322033898305085,
728
+ "grad_norm": 1.5468130653036234,
729
+ "learning_rate": 3.028456559074061e-06,
730
+ "loss": 0.4697,
731
+ "step": 102
732
+ },
733
+ {
734
+ "epoch": 0.4364406779661017,
735
+ "grad_norm": 1.6673377057588172,
736
+ "learning_rate": 2.9958831204577948e-06,
737
+ "loss": 0.4797,
738
+ "step": 103
739
+ },
740
+ {
741
+ "epoch": 0.4406779661016949,
742
+ "grad_norm": 1.447011897404953,
743
+ "learning_rate": 2.963221810217786e-06,
744
+ "loss": 0.4747,
745
+ "step": 104
746
+ },
747
+ {
748
+ "epoch": 0.4449152542372881,
749
+ "grad_norm": 1.432777576331977,
750
+ "learning_rate": 2.9304784160129535e-06,
751
+ "loss": 0.4507,
752
+ "step": 105
753
+ },
754
+ {
755
+ "epoch": 0.4491525423728814,
756
+ "grad_norm": 1.5026941312081397,
757
+ "learning_rate": 2.8976587400476804e-06,
758
+ "loss": 0.4918,
759
+ "step": 106
760
+ },
761
+ {
762
+ "epoch": 0.4533898305084746,
763
+ "grad_norm": 1.4223162678884775,
764
+ "learning_rate": 2.8647685980436547e-06,
765
+ "loss": 0.4457,
766
+ "step": 107
767
+ },
768
+ {
769
+ "epoch": 0.4576271186440678,
770
+ "grad_norm": 1.4862620244374363,
771
+ "learning_rate": 2.8318138182093053e-06,
772
+ "loss": 0.4484,
773
+ "step": 108
774
+ },
775
+ {
776
+ "epoch": 0.461864406779661,
777
+ "grad_norm": 2.325089744936281,
778
+ "learning_rate": 2.7988002402070346e-06,
779
+ "loss": 0.5083,
780
+ "step": 109
781
+ },
782
+ {
783
+ "epoch": 0.4661016949152542,
784
+ "grad_norm": 1.4973681427484284,
785
+ "learning_rate": 2.7657337141184137e-06,
786
+ "loss": 0.4645,
787
+ "step": 110
788
+ },
789
+ {
790
+ "epoch": 0.4703389830508475,
791
+ "grad_norm": 2.1380915604189767,
792
+ "learning_rate": 2.7326200994075364e-06,
793
+ "loss": 0.5214,
794
+ "step": 111
795
+ },
796
+ {
797
+ "epoch": 0.4745762711864407,
798
+ "grad_norm": 1.5610326724477157,
799
+ "learning_rate": 2.699465263882708e-06,
800
+ "loss": 0.4336,
801
+ "step": 112
802
+ },
803
+ {
804
+ "epoch": 0.4788135593220339,
805
+ "grad_norm": 1.5343886180839708,
806
+ "learning_rate": 2.666275082656656e-06,
807
+ "loss": 0.4566,
808
+ "step": 113
809
+ },
810
+ {
811
+ "epoch": 0.4830508474576271,
812
+ "grad_norm": 1.447579752768294,
813
+ "learning_rate": 2.6330554371054466e-06,
814
+ "loss": 0.467,
815
+ "step": 114
816
+ },
817
+ {
818
+ "epoch": 0.4872881355932203,
819
+ "grad_norm": 1.4056255209080681,
820
+ "learning_rate": 2.5998122138262944e-06,
821
+ "loss": 0.4492,
822
+ "step": 115
823
+ },
824
+ {
825
+ "epoch": 0.4915254237288136,
826
+ "grad_norm": 1.4635172681633466,
827
+ "learning_rate": 2.5665513035944373e-06,
828
+ "loss": 0.4699,
829
+ "step": 116
830
+ },
831
+ {
832
+ "epoch": 0.4957627118644068,
833
+ "grad_norm": 1.4586027588803236,
834
+ "learning_rate": 2.533278600319285e-06,
835
+ "loss": 0.4227,
836
+ "step": 117
837
+ },
838
+ {
839
+ "epoch": 0.5,
840
+ "grad_norm": 1.354229782865883,
841
+ "learning_rate": 2.5e-06,
842
+ "loss": 0.4425,
843
+ "step": 118
844
+ },
845
+ {
846
+ "epoch": 0.5042372881355932,
847
+ "grad_norm": 1.420361532173124,
848
+ "learning_rate": 2.466721399680716e-06,
849
+ "loss": 0.4548,
850
+ "step": 119
851
+ },
852
+ {
853
+ "epoch": 0.5084745762711864,
854
+ "grad_norm": 1.482111971980118,
855
+ "learning_rate": 2.4334486964055635e-06,
856
+ "loss": 0.4671,
857
+ "step": 120
858
+ },
859
+ {
860
+ "epoch": 0.5127118644067796,
861
+ "grad_norm": 1.752481879221272,
862
+ "learning_rate": 2.400187786173707e-06,
863
+ "loss": 0.4492,
864
+ "step": 121
865
+ },
866
+ {
867
+ "epoch": 0.5169491525423728,
868
+ "grad_norm": 1.513202782466588,
869
+ "learning_rate": 2.3669445628945543e-06,
870
+ "loss": 0.4836,
871
+ "step": 122
872
+ },
873
+ {
874
+ "epoch": 0.5211864406779662,
875
+ "grad_norm": 2.038288279694164,
876
+ "learning_rate": 2.3337249173433447e-06,
877
+ "loss": 0.459,
878
+ "step": 123
879
+ },
880
+ {
881
+ "epoch": 0.5254237288135594,
882
+ "grad_norm": 1.5013334194062444,
883
+ "learning_rate": 2.300534736117292e-06,
884
+ "loss": 0.4392,
885
+ "step": 124
886
+ },
887
+ {
888
+ "epoch": 0.5296610169491526,
889
+ "grad_norm": 1.463995793252121,
890
+ "learning_rate": 2.267379900592464e-06,
891
+ "loss": 0.4283,
892
+ "step": 125
893
+ },
894
+ {
895
+ "epoch": 0.5338983050847458,
896
+ "grad_norm": 1.4383774155895568,
897
+ "learning_rate": 2.234266285881587e-06,
898
+ "loss": 0.4611,
899
+ "step": 126
900
+ },
901
+ {
902
+ "epoch": 0.538135593220339,
903
+ "grad_norm": 1.361981138948913,
904
+ "learning_rate": 2.201199759792966e-06,
905
+ "loss": 0.432,
906
+ "step": 127
907
+ },
908
+ {
909
+ "epoch": 0.5423728813559322,
910
+ "grad_norm": 1.4043516358443713,
911
+ "learning_rate": 2.1681861817906955e-06,
912
+ "loss": 0.4412,
913
+ "step": 128
914
+ },
915
+ {
916
+ "epoch": 0.5466101694915254,
917
+ "grad_norm": 1.6529331980835023,
918
+ "learning_rate": 2.135231401956346e-06,
919
+ "loss": 0.463,
920
+ "step": 129
921
+ },
922
+ {
923
+ "epoch": 0.5508474576271186,
924
+ "grad_norm": 1.4224159024704217,
925
+ "learning_rate": 2.1023412599523204e-06,
926
+ "loss": 0.4583,
927
+ "step": 130
928
+ },
929
+ {
930
+ "epoch": 0.5550847457627118,
931
+ "grad_norm": 1.527284962476028,
932
+ "learning_rate": 2.069521583987048e-06,
933
+ "loss": 0.4451,
934
+ "step": 131
935
+ },
936
+ {
937
+ "epoch": 0.559322033898305,
938
+ "grad_norm": 1.441760395015376,
939
+ "learning_rate": 2.0367781897822147e-06,
940
+ "loss": 0.491,
941
+ "step": 132
942
+ },
943
+ {
944
+ "epoch": 0.5635593220338984,
945
+ "grad_norm": 1.3606273864846572,
946
+ "learning_rate": 2.004116879542205e-06,
947
+ "loss": 0.4596,
948
+ "step": 133
949
+ },
950
+ {
951
+ "epoch": 0.5677966101694916,
952
+ "grad_norm": 1.5064068994707893,
953
+ "learning_rate": 1.9715434409259393e-06,
954
+ "loss": 0.4908,
955
+ "step": 134
956
+ },
957
+ {
958
+ "epoch": 0.5720338983050848,
959
+ "grad_norm": 1.4023083759744266,
960
+ "learning_rate": 1.9390636460212803e-06,
961
+ "loss": 0.4634,
962
+ "step": 135
963
+ },
964
+ {
965
+ "epoch": 0.576271186440678,
966
+ "grad_norm": 1.442177828262353,
967
+ "learning_rate": 1.906683250322213e-06,
968
+ "loss": 0.4929,
969
+ "step": 136
970
+ },
971
+ {
972
+ "epoch": 0.5805084745762712,
973
+ "grad_norm": 1.5106296858321169,
974
+ "learning_rate": 1.874407991708957e-06,
975
+ "loss": 0.525,
976
+ "step": 137
977
+ },
978
+ {
979
+ "epoch": 0.5847457627118644,
980
+ "grad_norm": 1.4864793765676916,
981
+ "learning_rate": 1.8422435894311973e-06,
982
+ "loss": 0.4561,
983
+ "step": 138
984
+ },
985
+ {
986
+ "epoch": 0.5889830508474576,
987
+ "grad_norm": 1.3701351563038904,
988
+ "learning_rate": 1.8101957430946241e-06,
989
+ "loss": 0.4868,
990
+ "step": 139
991
+ },
992
+ {
993
+ "epoch": 0.5932203389830508,
994
+ "grad_norm": 1.3875578463356932,
995
+ "learning_rate": 1.7782701316509482e-06,
996
+ "loss": 0.4483,
997
+ "step": 140
998
+ },
999
+ {
1000
+ "epoch": 0.597457627118644,
1001
+ "grad_norm": 1.3844904134942564,
1002
+ "learning_rate": 1.7464724123915761e-06,
1003
+ "loss": 0.4596,
1004
+ "step": 141
1005
+ },
1006
+ {
1007
+ "epoch": 0.6016949152542372,
1008
+ "grad_norm": 1.4443438580562675,
1009
+ "learning_rate": 1.7148082199451288e-06,
1010
+ "loss": 0.4592,
1011
+ "step": 142
1012
+ },
1013
+ {
1014
+ "epoch": 0.6059322033898306,
1015
+ "grad_norm": 1.5342815602957074,
1016
+ "learning_rate": 1.6832831652789674e-06,
1017
+ "loss": 0.4581,
1018
+ "step": 143
1019
+ },
1020
+ {
1021
+ "epoch": 0.6101694915254238,
1022
+ "grad_norm": 1.4384876165227176,
1023
+ "learning_rate": 1.6519028347049242e-06,
1024
+ "loss": 0.4344,
1025
+ "step": 144
1026
+ },
1027
+ {
1028
+ "epoch": 0.614406779661017,
1029
+ "grad_norm": 1.6261082093464139,
1030
+ "learning_rate": 1.6206727888893875e-06,
1031
+ "loss": 0.485,
1032
+ "step": 145
1033
+ },
1034
+ {
1035
+ "epoch": 0.6186440677966102,
1036
+ "grad_norm": 1.3615799048062975,
1037
+ "learning_rate": 1.5895985618679447e-06,
1038
+ "loss": 0.4499,
1039
+ "step": 146
1040
+ },
1041
+ {
1042
+ "epoch": 0.6228813559322034,
1043
+ "grad_norm": 1.4754292550992594,
1044
+ "learning_rate": 1.5586856600647346e-06,
1045
+ "loss": 0.4567,
1046
+ "step": 147
1047
+ },
1048
+ {
1049
+ "epoch": 0.6271186440677966,
1050
+ "grad_norm": 1.4622934320148449,
1051
+ "learning_rate": 1.5279395613166987e-06,
1052
+ "loss": 0.4706,
1053
+ "step": 148
1054
+ },
1055
+ {
1056
+ "epoch": 0.6313559322033898,
1057
+ "grad_norm": 1.3842029005004872,
1058
+ "learning_rate": 1.4973657139028963e-06,
1059
+ "loss": 0.4277,
1060
+ "step": 149
1061
+ },
1062
+ {
1063
+ "epoch": 0.635593220338983,
1064
+ "grad_norm": 1.455925326020317,
1065
+ "learning_rate": 1.4669695355790552e-06,
1066
+ "loss": 0.4192,
1067
+ "step": 150
1068
+ },
1069
+ {
1070
+ "epoch": 0.6398305084745762,
1071
+ "grad_norm": 1.341652705806049,
1072
+ "learning_rate": 1.4367564126175338e-06,
1073
+ "loss": 0.4032,
1074
+ "step": 151
1075
+ },
1076
+ {
1077
+ "epoch": 0.6440677966101694,
1078
+ "grad_norm": 1.2879593544070345,
1079
+ "learning_rate": 1.4067316988528618e-06,
1080
+ "loss": 0.4176,
1081
+ "step": 152
1082
+ },
1083
+ {
1084
+ "epoch": 0.6483050847457628,
1085
+ "grad_norm": 1.4343959529464865,
1086
+ "learning_rate": 1.3769007147330282e-06,
1087
+ "loss": 0.4855,
1088
+ "step": 153
1089
+ },
1090
+ {
1091
+ "epoch": 0.652542372881356,
1092
+ "grad_norm": 1.405995087312755,
1093
+ "learning_rate": 1.347268746376685e-06,
1094
+ "loss": 0.4437,
1095
+ "step": 154
1096
+ },
1097
+ {
1098
+ "epoch": 0.6567796610169492,
1099
+ "grad_norm": 1.4998368455799236,
1100
+ "learning_rate": 1.3178410446364376e-06,
1101
+ "loss": 0.4453,
1102
+ "step": 155
1103
+ },
1104
+ {
1105
+ "epoch": 0.6610169491525424,
1106
+ "grad_norm": 1.3246088896656367,
1107
+ "learning_rate": 1.288622824168375e-06,
1108
+ "loss": 0.423,
1109
+ "step": 156
1110
+ },
1111
+ {
1112
+ "epoch": 0.6652542372881356,
1113
+ "grad_norm": 1.5177411918175312,
1114
+ "learning_rate": 1.2596192625080294e-06,
1115
+ "loss": 0.465,
1116
+ "step": 157
1117
+ },
1118
+ {
1119
+ "epoch": 0.6694915254237288,
1120
+ "grad_norm": 1.5546054605297754,
1121
+ "learning_rate": 1.230835499152901e-06,
1122
+ "loss": 0.477,
1123
+ "step": 158
1124
+ },
1125
+ {
1126
+ "epoch": 0.673728813559322,
1127
+ "grad_norm": 1.5460959768827836,
1128
+ "learning_rate": 1.202276634651724e-06,
1129
+ "loss": 0.4747,
1130
+ "step": 159
1131
+ },
1132
+ {
1133
+ "epoch": 0.6779661016949152,
1134
+ "grad_norm": 1.3946730571564074,
1135
+ "learning_rate": 1.1739477297006442e-06,
1136
+ "loss": 0.4463,
1137
+ "step": 160
1138
+ },
1139
+ {
1140
+ "epoch": 0.6822033898305084,
1141
+ "grad_norm": 1.4543786236975675,
1142
+ "learning_rate": 1.1458538042464477e-06,
1143
+ "loss": 0.4314,
1144
+ "step": 161
1145
+ },
1146
+ {
1147
+ "epoch": 0.6864406779661016,
1148
+ "grad_norm": 1.6349011430553178,
1149
+ "learning_rate": 1.1179998365970174e-06,
1150
+ "loss": 0.4633,
1151
+ "step": 162
1152
+ },
1153
+ {
1154
+ "epoch": 0.690677966101695,
1155
+ "grad_norm": 1.6684772506757712,
1156
+ "learning_rate": 1.0903907625391597e-06,
1157
+ "loss": 0.3939,
1158
+ "step": 163
1159
+ },
1160
+ {
1161
+ "epoch": 0.6949152542372882,
1162
+ "grad_norm": 1.4700700433376077,
1163
+ "learning_rate": 1.0630314744639831e-06,
1164
+ "loss": 0.4547,
1165
+ "step": 164
1166
+ },
1167
+ {
1168
+ "epoch": 0.6991525423728814,
1169
+ "grad_norm": 1.6884711897220055,
1170
+ "learning_rate": 1.0359268204999417e-06,
1171
+ "loss": 0.4544,
1172
+ "step": 165
1173
+ },
1174
+ {
1175
+ "epoch": 0.7033898305084746,
1176
+ "grad_norm": 1.4295382885254138,
1177
+ "learning_rate": 1.0090816036537462e-06,
1178
+ "loss": 0.4461,
1179
+ "step": 166
1180
+ },
1181
+ {
1182
+ "epoch": 0.7076271186440678,
1183
+ "grad_norm": 1.356516621935423,
1184
+ "learning_rate": 9.825005809592565e-07,
1185
+ "loss": 0.4134,
1186
+ "step": 167
1187
+ },
1188
+ {
1189
+ "epoch": 0.711864406779661,
1190
+ "grad_norm": 1.5555525661542857,
1191
+ "learning_rate": 9.561884626345206e-07,
1192
+ "loss": 0.4899,
1193
+ "step": 168
1194
+ },
1195
+ {
1196
+ "epoch": 0.7161016949152542,
1197
+ "grad_norm": 1.5462118141973062,
1198
+ "learning_rate": 9.301499112471205e-07,
1199
+ "loss": 0.4461,
1200
+ "step": 169
1201
+ },
1202
+ {
1203
+ "epoch": 0.7203389830508474,
1204
+ "grad_norm": 1.4436171388389583,
1205
+ "learning_rate": 9.043895408879505e-07,
1206
+ "loss": 0.4358,
1207
+ "step": 170
1208
+ },
1209
+ {
1210
+ "epoch": 0.7245762711864406,
1211
+ "grad_norm": 1.4723689458814584,
1212
+ "learning_rate": 8.789119163535875e-07,
1213
+ "loss": 0.443,
1214
+ "step": 171
1215
+ },
1216
+ {
1217
+ "epoch": 0.7288135593220338,
1218
+ "grad_norm": 1.4479515171719126,
1219
+ "learning_rate": 8.537215523374037e-07,
1220
+ "loss": 0.4332,
1221
+ "step": 172
1222
+ },
1223
+ {
1224
+ "epoch": 0.7330508474576272,
1225
+ "grad_norm": 1.4531321373130328,
1226
+ "learning_rate": 8.288229126295494e-07,
1227
+ "loss": 0.4423,
1228
+ "step": 173
1229
+ },
1230
+ {
1231
+ "epoch": 0.7372881355932204,
1232
+ "grad_norm": 1.4799542850821017,
1233
+ "learning_rate": 8.042204093259598e-07,
1234
+ "loss": 0.4513,
1235
+ "step": 174
1236
+ },
1237
+ {
1238
+ "epoch": 0.7415254237288136,
1239
+ "grad_norm": 1.4851037912394536,
1240
+ "learning_rate": 7.799184020465214e-07,
1241
+ "loss": 0.4446,
1242
+ "step": 175
1243
+ },
1244
+ {
1245
+ "epoch": 0.7457627118644068,
1246
+ "grad_norm": 1.4602481333866593,
1247
+ "learning_rate": 7.559211971625385e-07,
1248
+ "loss": 0.4516,
1249
+ "step": 176
1250
+ },
1251
+ {
1252
+ "epoch": 0.75,
1253
+ "grad_norm": 1.4428967944630504,
1254
+ "learning_rate": 7.322330470336314e-07,
1255
+ "loss": 0.4226,
1256
+ "step": 177
1257
+ },
1258
+ {
1259
+ "epoch": 0.7542372881355932,
1260
+ "grad_norm": 1.3466251631382284,
1261
+ "learning_rate": 7.088581492542121e-07,
1262
+ "loss": 0.4077,
1263
+ "step": 178
1264
+ },
1265
+ {
1266
+ "epoch": 0.7584745762711864,
1267
+ "grad_norm": 3.2305692134780544,
1268
+ "learning_rate": 6.858006459096603e-07,
1269
+ "loss": 0.4485,
1270
+ "step": 179
1271
+ },
1272
+ {
1273
+ "epoch": 0.7627118644067796,
1274
+ "grad_norm": 1.424216092114218,
1275
+ "learning_rate": 6.630646228423324e-07,
1276
+ "loss": 0.4288,
1277
+ "step": 180
1278
+ },
1279
+ {
1280
+ "epoch": 0.7669491525423728,
1281
+ "grad_norm": 1.4963321376713015,
1282
+ "learning_rate": 6.406541089275464e-07,
1283
+ "loss": 0.4477,
1284
+ "step": 181
1285
+ },
1286
+ {
1287
+ "epoch": 0.7711864406779662,
1288
+ "grad_norm": 1.692324873038992,
1289
+ "learning_rate": 6.185730753596538e-07,
1290
+ "loss": 0.4509,
1291
+ "step": 182
1292
+ },
1293
+ {
1294
+ "epoch": 0.7754237288135594,
1295
+ "grad_norm": 1.4105066699454112,
1296
+ "learning_rate": 5.968254349483332e-07,
1297
+ "loss": 0.4452,
1298
+ "step": 183
1299
+ },
1300
+ {
1301
+ "epoch": 0.7796610169491526,
1302
+ "grad_norm": 1.3982040439848404,
1303
+ "learning_rate": 5.754150414252341e-07,
1304
+ "loss": 0.456,
1305
+ "step": 184
1306
+ },
1307
+ {
1308
+ "epoch": 0.7838983050847458,
1309
+ "grad_norm": 1.4987411443142065,
1310
+ "learning_rate": 5.543456887610854e-07,
1311
+ "loss": 0.4866,
1312
+ "step": 185
1313
+ },
1314
+ {
1315
+ "epoch": 0.788135593220339,
1316
+ "grad_norm": 1.415837483472032,
1317
+ "learning_rate": 5.336211104933939e-07,
1318
+ "loss": 0.4635,
1319
+ "step": 186
1320
+ },
1321
+ {
1322
+ "epoch": 0.7923728813559322,
1323
+ "grad_norm": 1.4333258582601947,
1324
+ "learning_rate": 5.132449790648561e-07,
1325
+ "loss": 0.4453,
1326
+ "step": 187
1327
+ },
1328
+ {
1329
+ "epoch": 0.7966101694915254,
1330
+ "grad_norm": 1.4361430967251394,
1331
+ "learning_rate": 4.932209051725915e-07,
1332
+ "loss": 0.4045,
1333
+ "step": 188
1334
+ },
1335
+ {
1336
+ "epoch": 0.8008474576271186,
1337
+ "grad_norm": 1.4779140085188902,
1338
+ "learning_rate": 4.7355243712831565e-07,
1339
+ "loss": 0.4561,
1340
+ "step": 189
1341
+ },
1342
+ {
1343
+ "epoch": 0.8050847457627118,
1344
+ "grad_norm": 1.475897837842645,
1345
+ "learning_rate": 4.542430602295775e-07,
1346
+ "loss": 0.4603,
1347
+ "step": 190
1348
+ },
1349
+ {
1350
+ "epoch": 0.809322033898305,
1351
+ "grad_norm": 1.4126521358394666,
1352
+ "learning_rate": 4.3529619614215204e-07,
1353
+ "loss": 0.4428,
1354
+ "step": 191
1355
+ },
1356
+ {
1357
+ "epoch": 0.8135593220338984,
1358
+ "grad_norm": 1.5596603124840844,
1359
+ "learning_rate": 4.167152022937124e-07,
1360
+ "loss": 0.4501,
1361
+ "step": 192
1362
+ },
1363
+ {
1364
+ "epoch": 0.8177966101694916,
1365
+ "grad_norm": 1.5832611093442452,
1366
+ "learning_rate": 3.9850337127889245e-07,
1367
+ "loss": 0.4503,
1368
+ "step": 193
1369
+ },
1370
+ {
1371
+ "epoch": 0.8220338983050848,
1372
+ "grad_norm": 2.045166226749996,
1373
+ "learning_rate": 3.8066393027582276e-07,
1374
+ "loss": 0.5348,
1375
+ "step": 194
1376
+ },
1377
+ {
1378
+ "epoch": 0.826271186440678,
1379
+ "grad_norm": 1.5459560878753111,
1380
+ "learning_rate": 3.6320004047427414e-07,
1381
+ "loss": 0.4336,
1382
+ "step": 195
1383
+ },
1384
+ {
1385
+ "epoch": 0.8305084745762712,
1386
+ "grad_norm": 1.48708371974937,
1387
+ "learning_rate": 3.4611479651548456e-07,
1388
+ "loss": 0.447,
1389
+ "step": 196
1390
+ },
1391
+ {
1392
+ "epoch": 0.8347457627118644,
1393
+ "grad_norm": 1.4667687064435921,
1394
+ "learning_rate": 3.2941122594378235e-07,
1395
+ "loss": 0.4088,
1396
+ "step": 197
1397
+ },
1398
+ {
1399
+ "epoch": 0.8389830508474576,
1400
+ "grad_norm": 1.4339420790789368,
1401
+ "learning_rate": 3.130922886700968e-07,
1402
+ "loss": 0.4462,
1403
+ "step": 198
1404
+ },
1405
+ {
1406
+ "epoch": 0.8432203389830508,
1407
+ "grad_norm": 1.433293475147707,
1408
+ "learning_rate": 2.9716087644745844e-07,
1409
+ "loss": 0.4717,
1410
+ "step": 199
1411
+ },
1412
+ {
1413
+ "epoch": 0.847457627118644,
1414
+ "grad_norm": 2.254627330176421,
1415
+ "learning_rate": 2.8161981235857145e-07,
1416
+ "loss": 0.4848,
1417
+ "step": 200
1418
+ },
1419
+ {
1420
+ "epoch": 0.847457627118644,
1421
+ "eval_loss": 0.40594419836997986,
1422
+ "eval_runtime": 5.1423,
1423
+ "eval_samples_per_second": 0.194,
1424
+ "eval_steps_per_second": 0.194,
1425
+ "step": 200
1426
+ },
1427
+ {
1428
+ "epoch": 0.8516949152542372,
1429
+ "grad_norm": 1.4766035519752403,
1430
+ "learning_rate": 2.664718503155561e-07,
1431
+ "loss": 0.4712,
1432
+ "step": 201
1433
+ },
1434
+ {
1435
+ "epoch": 0.8559322033898306,
1436
+ "grad_norm": 1.4898631745936681,
1437
+ "learning_rate": 2.517196745719522e-07,
1438
+ "loss": 0.4493,
1439
+ "step": 202
1440
+ },
1441
+ {
1442
+ "epoch": 0.8601694915254238,
1443
+ "grad_norm": 1.3912238047826437,
1444
+ "learning_rate": 2.3736589924706065e-07,
1445
+ "loss": 0.4505,
1446
+ "step": 203
1447
+ },
1448
+ {
1449
+ "epoch": 0.864406779661017,
1450
+ "grad_norm": 1.4391187633818725,
1451
+ "learning_rate": 2.2341306786271695e-07,
1452
+ "loss": 0.4511,
1453
+ "step": 204
1454
+ },
1455
+ {
1456
+ "epoch": 0.8686440677966102,
1457
+ "grad_norm": 1.3358943208854202,
1458
+ "learning_rate": 2.098636528925732e-07,
1459
+ "loss": 0.4118,
1460
+ "step": 205
1461
+ },
1462
+ {
1463
+ "epoch": 0.8728813559322034,
1464
+ "grad_norm": 2.140928875781542,
1465
+ "learning_rate": 1.967200553239676e-07,
1466
+ "loss": 0.5221,
1467
+ "step": 206
1468
+ },
1469
+ {
1470
+ "epoch": 0.8771186440677966,
1471
+ "grad_norm": 1.5517467663817437,
1472
+ "learning_rate": 1.839846042324686e-07,
1473
+ "loss": 0.4514,
1474
+ "step": 207
1475
+ },
1476
+ {
1477
+ "epoch": 0.8813559322033898,
1478
+ "grad_norm": 1.666553803897623,
1479
+ "learning_rate": 1.7165955636915395e-07,
1480
+ "loss": 0.4854,
1481
+ "step": 208
1482
+ },
1483
+ {
1484
+ "epoch": 0.885593220338983,
1485
+ "grad_norm": 1.5675665553210052,
1486
+ "learning_rate": 1.5974709576071e-07,
1487
+ "loss": 0.4445,
1488
+ "step": 209
1489
+ },
1490
+ {
1491
+ "epoch": 0.8898305084745762,
1492
+ "grad_norm": 1.4022593911682197,
1493
+ "learning_rate": 1.4824933332241693e-07,
1494
+ "loss": 0.4384,
1495
+ "step": 210
1496
+ },
1497
+ {
1498
+ "epoch": 0.8940677966101694,
1499
+ "grad_norm": 1.5001934782227526,
1500
+ "learning_rate": 1.371683064840912e-07,
1501
+ "loss": 0.4244,
1502
+ "step": 211
1503
+ },
1504
+ {
1505
+ "epoch": 0.8983050847457628,
1506
+ "grad_norm": 1.4677066964876824,
1507
+ "learning_rate": 1.265059788290468e-07,
1508
+ "loss": 0.4532,
1509
+ "step": 212
1510
+ },
1511
+ {
1512
+ "epoch": 0.902542372881356,
1513
+ "grad_norm": 1.4183398497893178,
1514
+ "learning_rate": 1.1626423974614414e-07,
1515
+ "loss": 0.4366,
1516
+ "step": 213
1517
+ },
1518
+ {
1519
+ "epoch": 0.9067796610169492,
1520
+ "grad_norm": 1.6894490357590148,
1521
+ "learning_rate": 1.0644490409498636e-07,
1522
+ "loss": 0.4623,
1523
+ "step": 214
1524
+ },
1525
+ {
1526
+ "epoch": 0.9110169491525424,
1527
+ "grad_norm": 1.3770052672043003,
1528
+ "learning_rate": 9.704971188432166e-08,
1529
+ "loss": 0.435,
1530
+ "step": 215
1531
+ },
1532
+ {
1533
+ "epoch": 0.9152542372881356,
1534
+ "grad_norm": 1.3141039953147144,
1535
+ "learning_rate": 8.808032796371019e-08,
1536
+ "loss": 0.4256,
1537
+ "step": 216
1538
+ },
1539
+ {
1540
+ "epoch": 0.9194915254237288,
1541
+ "grad_norm": 1.8544440786448932,
1542
+ "learning_rate": 7.953834172850866e-08,
1543
+ "loss": 0.5039,
1544
+ "step": 217
1545
+ },
1546
+ {
1547
+ "epoch": 0.923728813559322,
1548
+ "grad_norm": 1.450368984214262,
1549
+ "learning_rate": 7.142526683822537e-08,
1550
+ "loss": 0.4554,
1551
+ "step": 218
1552
+ },
1553
+ {
1554
+ "epoch": 0.9279661016949152,
1555
+ "grad_norm": 1.315431283646059,
1556
+ "learning_rate": 6.374254094829723e-08,
1557
+ "loss": 0.4183,
1558
+ "step": 219
1559
+ },
1560
+ {
1561
+ "epoch": 0.9322033898305084,
1562
+ "grad_norm": 1.3792458791734967,
1563
+ "learning_rate": 5.649152545533332e-08,
1564
+ "loss": 0.4348,
1565
+ "step": 220
1566
+ },
1567
+ {
1568
+ "epoch": 0.9364406779661016,
1569
+ "grad_norm": 1.3346772573887995,
1570
+ "learning_rate": 4.967350525587305e-08,
1571
+ "loss": 0.4161,
1572
+ "step": 221
1573
+ },
1574
+ {
1575
+ "epoch": 0.940677966101695,
1576
+ "grad_norm": 1.5577152328331694,
1577
+ "learning_rate": 4.328968851869758e-08,
1578
+ "loss": 0.4828,
1579
+ "step": 222
1580
+ },
1581
+ {
1582
+ "epoch": 0.9449152542372882,
1583
+ "grad_norm": 1.3732105413808344,
1584
+ "learning_rate": 3.7341206470742355e-08,
1585
+ "loss": 0.464,
1586
+ "step": 223
1587
+ },
1588
+ {
1589
+ "epoch": 0.9491525423728814,
1590
+ "grad_norm": 1.449997180723802,
1591
+ "learning_rate": 3.182911319663862e-08,
1592
+ "loss": 0.46,
1593
+ "step": 224
1594
+ },
1595
+ {
1596
+ "epoch": 0.9533898305084746,
1597
+ "grad_norm": 1.4758185761477316,
1598
+ "learning_rate": 2.6754385451928655e-08,
1599
+ "loss": 0.4428,
1600
+ "step": 225
1601
+ },
1602
+ {
1603
+ "epoch": 0.9576271186440678,
1604
+ "grad_norm": 1.3814801872524662,
1605
+ "learning_rate": 2.211792248998229e-08,
1606
+ "loss": 0.4226,
1607
+ "step": 226
1608
+ },
1609
+ {
1610
+ "epoch": 0.961864406779661,
1611
+ "grad_norm": 1.4632888436552436,
1612
+ "learning_rate": 1.7920545902646026e-08,
1613
+ "loss": 0.4297,
1614
+ "step": 227
1615
+ },
1616
+ {
1617
+ "epoch": 0.9661016949152542,
1618
+ "grad_norm": 1.4229121228644899,
1619
+ "learning_rate": 1.4162999474657268e-08,
1620
+ "loss": 0.4597,
1621
+ "step": 228
1622
+ },
1623
+ {
1624
+ "epoch": 0.9703389830508474,
1625
+ "grad_norm": 1.333969805143941,
1626
+ "learning_rate": 1.0845949051841442e-08,
1627
+ "loss": 0.4038,
1628
+ "step": 229
1629
+ },
1630
+ {
1631
+ "epoch": 0.9745762711864406,
1632
+ "grad_norm": 1.514340734500005,
1633
+ "learning_rate": 7.96998242312469e-09,
1634
+ "loss": 0.4555,
1635
+ "step": 230
1636
+ },
1637
+ {
1638
+ "epoch": 0.9788135593220338,
1639
+ "grad_norm": 1.4123054627528595,
1640
+ "learning_rate": 5.535609216374971e-09,
1641
+ "loss": 0.4401,
1642
+ "step": 231
1643
+ },
1644
+ {
1645
+ "epoch": 0.9830508474576272,
1646
+ "grad_norm": 1.332429400203387,
1647
+ "learning_rate": 3.5432608080951392e-09,
1648
+ "loss": 0.4276,
1649
+ "step": 232
1650
+ },
1651
+ {
1652
+ "epoch": 0.9872881355932204,
1653
+ "grad_norm": 1.540606352993932,
1654
+ "learning_rate": 1.9932902469829707e-09,
1655
+ "loss": 0.4418,
1656
+ "step": 233
1657
+ },
1658
+ {
1659
+ "epoch": 0.9915254237288136,
1660
+ "grad_norm": 1.4786831530095756,
1661
+ "learning_rate": 8.859721913684339e-10,
1662
+ "loss": 0.4684,
1663
+ "step": 234
1664
+ },
1665
+ {
1666
+ "epoch": 0.9957627118644068,
1667
+ "grad_norm": 1.7669414061558033,
1668
+ "learning_rate": 2.2150286054567482e-10,
1669
+ "loss": 0.4722,
1670
+ "step": 235
1671
+ },
1672
+ {
1673
+ "epoch": 1.0,
1674
+ "grad_norm": 1.3471984612585037,
1675
+ "learning_rate": 0.0,
1676
+ "loss": 0.4229,
1677
+ "step": 236
1678
+ },
1679
+ {
1680
+ "epoch": 1.0,
1681
+ "step": 236,
1682
+ "total_flos": 11901468672000.0,
1683
+ "train_loss": 0.4903946296643403,
1684
+ "train_runtime": 2458.2804,
1685
+ "train_samples_per_second": 0.383,
1686
+ "train_steps_per_second": 0.096
1687
+ }
1688
+ ],
1689
+ "logging_steps": 1,
1690
+ "max_steps": 236,
1691
+ "num_input_tokens_seen": 0,
1692
+ "num_train_epochs": 1,
1693
+ "save_steps": 2000000,
1694
+ "stateful_callbacks": {
1695
+ "TrainerControl": {
1696
+ "args": {
1697
+ "should_epoch_stop": false,
1698
+ "should_evaluate": false,
1699
+ "should_log": false,
1700
+ "should_save": true,
1701
+ "should_training_stop": true
1702
+ },
1703
+ "attributes": {}
1704
+ }
1705
+ },
1706
+ "total_flos": 11901468672000.0,
1707
+ "train_batch_size": 1,
1708
+ "trial_name": null,
1709
+ "trial_params": null
1710
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27d3f3634dce6c7a5108448164727d1f6de787b2df1426c7629da8fe62be90ae
3
+ size 7569
training_eval_loss.png ADDED
training_loss.png ADDED